© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29307
    Prev
    Next
    INDEX
    Explanations

    mentions of the Olympic Games and related events

    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
    759
    +0.10
    0.4%
    445
    +0.09
    0.4%
    116
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.03
    146
    +0.09
    0.02
    97
    +0.09
    0.01
    Negative Logits
    arial
    -0.74
    stocks
    -0.73
    ouri
    -0.69
    ociate
    -0.68
    fork
    -0.67
    othal
    -0.66
    drawn
    -0.66
    iri
    -0.66
    roid
    -0.65
     Mustang
    -0.65
    POSITIVE LOGITS
     Torch
    0.94
     Games
    0.85
    lymp
    0.82
     Trials
    0.72
     torch
    0.72
    wald
    0.70
     medal
    0.69
     medals
    0.67
     Olympics
    0.67
     Athlet
    0.67
    Activations Density 0.356%

    No Known Activations