© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 25951
    Prev
    Next
    INDEX
    Explanations

    phrases indicating addition or continuation in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    500
    +0.17
    0.9%
    393
    +0.12
    0.7%
    200
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.17
    0.08
    257
    +0.12
    0.05
    78
    +0.12
    0.06
    Negative Logits
     section
    -1.62
     above
    -1.44
    grounds
    -1.42
     language
    -1.39
    cca
    -1.39
    RA
    -1.38
     below
    -1.35
    Saharan
    -1.33
    bert
    -1.32
     history
    -1.29
    POSITIVE LOGITS
    amily
    1.70
     DAMAGE
    1.69
    ){#
    1.63
    alities
    1.48
    ão
    1.45
    ----------------------------------------------------------------------------------------------------------------
    1.43
    --------------------------------------------------------------------------------------------------------------------------------
    1.39
    Ł
    1.38
    IAL
    1.37
    ashes
    1.36
    Activations Density 0.763%

    No Known Activations