© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26379
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of returning or going back

    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
    374
    +0.11
    0.6%
    125
    +0.11
    0.6%
    256
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.11
    0.03
    256
    +0.11
    0.04
    62
    +0.10
    0.03
    Negative Logits
    ĵ
    -3.01
    «
    -2.84
    §
    -2.81
    ĩ
    -2.76
    ¯
    -2.71
    Ĩ
    -2.55
    ¢
    -2.53
    ½
    -2.53
    ©
    -2.49
    ĥ½
    -2.48
    POSITIVE LOGITS
    door
    2.24
    tracking
    1.93
    dated
    1.87
    lund
    1.82
    wards
    1.78
    fires
    1.77
    woods
    1.77
    doors
    1.76
    haul
    1.69
    ordered
    1.67
    Activations Density 0.122%

    No Known Activations