© 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. 28214
    Prev
    Next
    INDEX
    Explanations

    function definitions and declarations

    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
    369
    +0.15
    0.8%
    123
    +0.12
    0.7%
    254
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.15
    0.03
    486
    +0.12
    0.03
    123
    +0.11
    0.03
    Negative Logits
    place
    -1.59
    said
    -1.43
    version
    -1.41
    EventArgs
    -1.41
    lik
    -1.40
    ten
    -1.34
    Mill
    -1.33
    Observer
    -1.28
    voltage
    -1.28
     view
    -1.28
    POSITIVE LOGITS
    ĥ½
    2.74
    Į
    2.55
    ģ
    2.50
    ī
    2.35
    §
    2.30
    Īĺ
    2.27
    İ
    2.27
    °
    2.20
    Ļ
    2.18
    į
    2.17
    Activations Density 0.060%

    No Known Activations