© 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 EvalsExportsinterp-engineNEWAPI 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. 7353
    Prev
    Next
    INDEX
    Explanations

    terms related to groups or organized units, particularly those associated with squads or teams

    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
    274
    +0.10
    0.5%
    496
    +0.10
    0.5%
    685
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.03
    537
    +0.10
    0.02
    659
    +0.09
    0.02
    Negative Logits
    ocaust
    -0.83
     Nanto
    -0.79
    istically
    -0.71
    ãĤ´ãĥ³
    -0.71
    xual
    -0.69
    ãĥ¼ãĥ³
    -0.69
    emort
    -0.68
    utenberg
    -0.67
    ä
    -0.65
    ught
    -0.63
    POSITIVE LOGITS
    rons
    1.31
    bury
    0.78
    irrel
    0.76
    ard
    0.75
    rim
    0.73
    bour
    0.73
    elve
    0.71
    ropolitan
    0.70
    mers
    0.70
    dies
    0.69
    Activations Density 0.171%

    No Known Activations