© 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. 10-RES_POST_32K-OAI
    11. 32494
    Prev
    Next
    INDEX
    Explanations

    references to research studies and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    373
    +0.18
    0.8%
    615
    +0.09
    0.4%
    171
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.18
    0.10
    145
    +0.09
    0.08
    622
    +0.09
    0.06
    Negative Logits
    thumbnails
    -0.76
    yx
    -0.74
    tumblr
    -0.73
    myra
    -0.68
    aby
    -0.68
    bub
    -0.66
    cks
    -0.66
    ãģ¯
    -0.66
    cius
    -0.64
    ãĤĤ
    -0.63
    POSITIVE LOGITS
     JUSTICE
    0.97
     Notwithstanding
    0.83
     Similarly
    0.80
     Cf
    0.78
     Accordingly
    0.74
     Although
    0.73
     Clearly
    0.72
     Effective
    0.71
     Presumably
    0.71
     Defendant
    0.71
    Activations Density 0.341%

    No Known Activations