© 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. 1-RES-SM
    11. 25552
    Prev
    Next
    INDEX
    Explanations

    the concluding parts of sentences or documents

    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
    194
    +0.12
    0.7%
    239
    +0.11
    0.6%
    365
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.12
    0.04
    33
    +0.11
    0.03
    468
    +0.10
    0.03
    Negative Logits
    »¿
    -2.69
    ŀ
    -2.55
    ½
    -2.36
    ¢
    -2.19
    ¾
    -2.09
    Į
    -2.06
    ĻĤ
    -1.99
    ĵ
    -1.97
    ¿
    -1.88
    ¶
    -1.83
    POSITIVE LOGITS
    piece
    1.85
    lessly
    1.81
    omorphisms
    1.79
    odontic
    1.76
    oplasmic
    1.75
    angered
    1.71
    ows
    1.69
    ajan
    1.68
    ennial
    1.66
    game
    1.58
    Activations Density 0.169%

    No Known Activations