© 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. 2-RES-SM
    11. 13509
    Prev
    Next
    INDEX
    Explanations

    elements associated with programming and web development, particularly related to HTML and database management

    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
    181
    +0.12
    0.7%
    133
    +0.12
    0.7%
    509
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.12
    0.20
    47
    +0.12
    0.20
    53
    +0.11
    0.18
    Negative Logits
     yours
    -1.75
    alian
    -1.60
    ests
    -1.57
    amble
    -1.54
     myself
    -1.53
    ark
    -1.49
     so
    -1.44
    agram
    -1.43
    erville
    -1.40
    essa
    -1.37
    POSITIVE LOGITS
    disambiguation
    1.47
    ).](
    1.38
     Giul
    1.38
    cies
    1.36
    ?).
    1.33
     banks
    1.33
     gases
    1.31
     flames
    1.30
    sson
    1.27
    ="../../../
    1.27
    Activations Density 4.816%

    No Known Activations