© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11745
    Prev
    Next
    INDEX
    Explanations

    mentions of files, categories, and materials

    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
    160
    +0.13
    0.7%
    83
    +0.12
    0.7%
    255
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.13
    0.00
    78
    +0.12
    -0.00
    255
    +0.11
    -0.00
    Negative Logits
    psin
    -1.45
     slightest
    -1.42
    TES
    -1.38
    ¦
    -1.36
     husband
    -1.34
    ķ
    -1.33
    ĥ½
    -1.29
     viewer
    -1.29
     translate
    -1.28
     Zend
    -1.27
    POSITIVE LOGITS
     invented
    1.81
     erected
    1.67
     of
    1.51
     introduced
    1.47
    artments
    1.46
     inhabited
    1.46
     coined
    1.43
    )\*
    1.43
     belonging
    1.43
     undertaken
    1.42
    Activations Density 0.021%

    No Known Activations