© 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. 29336
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific JavaScript code elements

    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
    295
    +0.15
    0.8%
    109
    +0.14
    0.8%
    495
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.15
    0.01
    157
    +0.14
    0.02
    495
    +0.13
    0.01
    Negative Logits
    ĥ
    -2.44
    Ĭ
    -2.23
    ĩ
    -2.16
    Ħ
    -2.10
    Ģ
    -2.03
    »
    -2.03
    ī
    -2.02
    ¯
    -1.97
    ³
    -1.92
    -1.89
    POSITIVE LOGITS
    ingo
    1.62
    vern
    1.54
    CRIPT
    1.53
    sie
    1.51
    script
    1.49
    hift
    1.48
    orro
    1.46
     party
    1.45
    olev
    1.44
    obar
    1.44
    Activations Density 0.066%

    No Known Activations