© 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. 7161
    Prev
    Next
    INDEX
    Explanations

    descriptors of player attributes and skills in sports contexts

    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
    634
    +0.15
    0.7%
    468
    +0.14
    0.6%
    264
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.10
    540
    +0.14
    0.08
    634
    +0.10
    0.07
    Negative Logits
     CODE
    -0.86
     ABE
    -0.83
    abus
    -0.74
     Badge
    -0.68
     Pai
    -0.67
     Appeals
    -0.67
     Seat
    -0.66
     Resp
    -0.66
     Pledge
    -0.64
     Advertising
    -0.64
    POSITIVE LOGITS
     defic
    0.88
     extraord
    0.86
     offensively
    0.84
     firepower
    0.84
     performer
    0.82
     combination
    0.80
     oriented
    0.80
     calib
    0.78
     powerhouse
    0.78
     prowess
    0.76
    Activations Density 0.983%

    No Known Activations