© 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. 8-RES_POST_32K-OAI
    11. 6552
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific sports positions or statistics

    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
    603
    +0.11
    0.5%
    339
    +0.11
    0.5%
    141
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    589
    +0.11
    0.05
    371
    +0.11
    0.06
    362
    +0.11
    0.06
    Negative Logits
    Leaks
    -0.82
     guiActiveUnfocused
    -0.78
    SPONSORED
    -0.76
     Bezos
    -0.74
    emet
    -0.73
     Donation
    -0.73
    sonian
    -0.71
     "$:/
    -0.69
     Cheong
    -0.67
     Canaver
    -0.65
    POSITIVE LOGITS
    iba
    0.86
    vol
    0.74
     fullback
    0.70
     shortstop
    0.66
    olver
    0.65
     QB
    0.64
    hell
    0.64
    ãģĭ
    0.63
     quarterback
    0.63
    hooting
    0.62
    Activations Density 0.317%

    No Known Activations