© 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 EvalsExportsAPI 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. 28396
    Prev
    Next
    INDEX
    Explanations

    terms related to internet domains and websites

    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
    649
    +0.13
    0.6%
    366
    +0.12
    0.6%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.02
    404
    +0.12
    0.02
    288
    +0.11
    0.03
    Negative Logits
    INGTON
    -0.86
    nut
    -0.85
    nuts
    -0.82
    ood
    -0.77
    wards
    -0.77
    aii
    -0.76
    ington
    -0.76
    noon
    -0.73
    recated
    -0.71
     "$:/
    -0.71
    POSITIVE LOGITS
    chnology
    1.22
    lli
    1.11
    geist
    0.84
    lla
    0.83
    chn
    0.75
    llo
    0.69
    gregation
    0.69
    fish
    0.69
    brate
    0.67
    pec
    0.67
    Activations Density 0.228%

    No Known Activations