© 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. 4-RES-SM
    11. 14765
    Prev
    Next
    INDEX
    Explanations

    references to collective actions or partnerships

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    68
    +0.12
    0.7%
    172
    +0.12
    0.6%
    343
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.12
    0.03
    309
    +0.12
    0.02
    448
    +0.11
    0.02
    Negative Logits
    wegian
    -1.97
    ared
    -1.93
    ureus
    -1.79
    rès
    -1.74
    heets
    -1.74
    ¦
    -1.73
    orrow
    -1.67
    asio
    -1.65
    nier
    -1.60
    ides
    -1.58
    POSITIVE LOGITS
     venture
    2.43
     ventures
    2.19
    ed
    2.12
     agreement
    1.86
     joint
    1.78
     between
    1.76
    ees
    1.66
     arthro
    1.65
     motion
    1.62
     chiefs
    1.62
    Activations Density 0.178%

    No Known Activations