© 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. 7582
    Prev
    Next
    INDEX
    Explanations

    references to sports contracts and player assessments

    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
    86
    +0.12
    0.5%
    583
    +0.11
    0.5%
    625
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.14
    94
    +0.11
    0.10
    143
    +0.09
    0.09
    Negative Logits
    orno
    -0.76
    sie
    -0.75
     Nath
    -0.74
     SX
    -0.70
    SPONSORED
    -0.70
     Feminist
    -0.69
    tel
    -0.68
     UNESCO
    -0.67
    ijing
    -0.66
     Quartz
    -0.65
    POSITIVE LOGITS
     offseason
    1.19
    Coach
    1.12
     playoff
    1.09
     quarterback
    1.05
     Bucs
    1.04
     coaching
    1.04
     coaches
    1.03
    Players
    1.03
     Defensive
    1.02
     Playoff
    1.02
    Activations Density 0.584%

    No Known Activations