© 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. 10-RES_POST_32K-OAI
    11. 29951
    Prev
    Next
    INDEX
    Explanations

    information related to specific individuals, events, or numerical data

    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
    100
    +0.13
    0.6%
    711
    +0.12
    0.6%
    476
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.15
    103
    +0.12
    0.10
    591
    +0.11
    0.08
    Negative Logits
     Greenberg
    -0.96
     thous
    -0.85
    ------------------------
    -0.84
     Epic
    -0.80
     Lep
    -0.79
    igil
    -0.75
    Merc
    -0.75
     cous
    -0.74
     recomm
    -0.73
     Huss
    -0.73
    POSITIVE LOGITS
    elta
    0.88
    56
    0.86
    176
    0.82
    196
    0.78
    ately
    0.77
    116
    0.77
    rates
    0.77
    gil
    0.76
    ATES
    0.76
     86
    0.75
    Activations Density 4.965%

    No Known Activations