© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 30882
    Prev
    Next
    INDEX
    Explanations

    references to influential figures or entities within societal contexts

    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
    246
    +0.12
    0.5%
    8
    +0.11
    0.5%
    264
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.18
    608
    +0.11
    0.13
    393
    +0.10
    0.10
    Negative Logits
     schedules
    -0.75
     targets
    -0.73
     supplies
    -0.73
    Results
    -0.72
     counterparts
    -0.69
     superiors
    -0.69
     purchases
    -0.68
     shipments
    -0.68
     patches
    -0.67
     locations
    -0.66
    POSITIVE LOGITS
     millennial
    0.85
     modern
    0.84
     Enlightenment
    0.81
     twentieth
    0.78
     Renaissance
    0.77
     millennium
    0.76
     21
    0.76
     apocalypse
    0.75
     underdog
    0.73
     postwar
    0.73
    Activations Density 0.933%

    No Known Activations