© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 28032
    Prev
    Next
    INDEX
    Explanations

    references to quantities or counts associated with various subjects

    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
    442
    +0.18
    1.0%
    12
    +0.14
    0.8%
    195
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.18
    0.06
    10
    +0.14
    0.04
    12
    +0.12
    0.03
    Negative Logits
    ´
    -4.90
    ¡
    -4.84
    Ŀ
    -4.71
    ĭ
    -4.70
    ©
    -4.66
    ŀ
    -4.64
    Ī
    -4.63
    ī
    -4.55
    Ĩ
    -4.55
    ½
    -4.53
    POSITIVE LOGITS
     testified
    1.51
     advice
    1.36
     asc
    1.35
     appellant
    1.32
     rehearing
    1.31
    agogue
    1.26
     Alaska
    1.26
    cient
    1.25
     ancient
    1.24
     resin
    1.24
    Activations Density 0.574%

    No Known Activations