© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7212
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "to" with varying frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    608
    +0.23
    1.1%
    393
    +0.17
    0.8%
    362
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.23
    0.14
    669
    +0.17
    0.09
    549
    +0.13
    0.06
    Negative Logits
     went
    -0.76
    llo
    -0.76
    quartered
    -0.74
    awei
    -0.74
    ãģ®éŃĶ
    -0.73
    NESS
    -0.73
    sky
    -0.72
    lli
    -0.72
    verning
    -0.70
    nder
    -0.69
    POSITIVE LOGITS
     the
    0.96
     those
    0.89
     their
    0.83
     our
    0.82
     its
    0.82
     another
    0.82
     a
    0.77
     an
    0.76
     some
    0.74
     them
    0.74
    Activations Density 0.787%

    No Known Activations