© 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. 5279
    Prev
    Next
    INDEX
    Explanations

    numeric values and potentially their relevance in scientific or statistical contexts

    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
    421
    +0.11
    0.5%
    651
    +0.11
    0.5%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.11
    0.06
    472
    +0.11
    0.04
    6
    +0.10
    0.06
    Negative Logits
    ary
    -0.74
    gur
    -0.72
    gart
    -0.69
    enez
    -0.69
    marked
    -0.68
    ain
    -0.64
     gland
    -0.64
    UTH
    -0.62
    ged
    -0.62
    nant
    -0.61
    POSITIVE LOGITS
    okers
    0.90
    obyl
    0.88
    oker
    0.81
    ãĥ¼ãĥ«
    0.79
    elly
    0.71
    thia
    0.71
    ople
    0.71
    ly
    0.70
    fts
    0.70
    ters
    0.69
    Activations Density 0.313%

    No Known Activations