© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4953
    Prev
    Next
    INDEX
    Explanations

    mentions of "variable" in a programming or mathematical context

    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
    623
    +0.14
    0.6%
    457
    +0.11
    0.5%
    609
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.14
    0.02
    540
    +0.11
    0.02
    255
    +0.11
    0.02
    Negative Logits
    lyak
    -0.79
     Kirin
    -0.77
    Ĥª
    -0.77
    ļé
    -0.76
    furt
    -0.75
    Ķ
    -0.74
    llah
    -0.72
    İ
    -0.69
    avorite
    -0.69
    hovah
    -0.68
    POSITIVE LOGITS
    ially
    0.74
    izable
    0.71
    variable
    0.71
    iety
    0.70
    izations
    0.69
    iveness
    0.66
    wine
    0.66
    binding
    0.66
    uating
    0.65
    isation
    0.65
    Activations Density 0.051%

    No Known Activations