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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4567
    Prev
    Next
    INDEX
    Explanations

    expressions of individual freedom and personal agency

    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
    464
    +0.11
    0.5%
    654
    +0.11
    0.5%
    473
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.15
    762
    +0.11
    0.17
    8
    +0.10
    0.12
    Negative Logits
    âĹ¼
    -0.79
    laughs
    -0.72
     anecd
    -0.71
    htaking
    -0.68
     Previously
    -0.67
    Laughs
    -0.67
     *)
    -0.66
     Slightly
    -0.66
    umably
    -0.65
     Possibly
    -0.64
    POSITIVE LOGITS
     belongs
    0.78
    verning
    0.74
     belong
    0.72
     survival
    0.69
     condem
    0.64
    ichever
    0.64
     Kham
    0.64
     vanquished
    0.63
    stood
    0.63
    tera
    0.63
    Activations Density 3.740%

    No Known Activations