© 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. 8129
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and functions in programming code

    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
    359
    +0.12
    0.6%
    104
    +0.09
    0.4%
    255
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    692
    +0.12
    0.04
    326
    +0.09
    0.04
    701
    +0.09
    0.04
    Negative Logits
    20439
    -0.91
    DVD
    -0.84
    rontal
    -0.71
    ĸļ
    -0.71
    Lago
    -0.70
    bench
    -0.70
    ãĥīãĥ©
    -0.70
    Hyd
    -0.65
    cffffcc
    -0.65
    LLOW
    -0.65
    POSITIVE LOGITS
     {}
    0.77
     contents
    0.77
     NULL
    0.75
     self
    0.75
     null
    0.74
     value
    0.74
     {
    0.74
     these
    0.74
     ({
    0.73
     parsed
    0.73
    Activations Density 0.205%

    No Known Activations