© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 27409
    Prev
    Next
    INDEX
    Explanations

    references to events or occasions requiring community or volunteer participation

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    6
    +0.13
    0.7%
    161
    +0.12
    0.7%
    240
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.13
    0.15
    496
    +0.12
    0.13
    492
    +0.12
    0.08
    Negative Logits
    keit
    -1.64
    inux
    -1.64
     ^[@
    -1.47
    IEW
    -1.42
     appliances
    -1.38
     Applications
    -1.37
    zzo
    -1.35
    pect
    -1.31
    baum
    -1.30
     Fans
    -1.27
    POSITIVE LOGITS
    istically
    1.69
    ward
    1.56
    creation
    1.47
     probability
    1.44
     wrath
    1.44
    message
    1.43
    veis
    1.40
    ils
    1.38
    phon
    1.38
    ships
    1.34
    Activations Density 5.408%

    No Known Activations