© 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. 10-RES_POST_32K-OAI
    11. 28391
    Prev
    Next
    INDEX
    Explanations

    terms related to defensive positions in sports, particularly football

    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
    373
    +0.12
    0.6%
    759
    +0.11
    0.5%
    620
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.12
    0.02
    288
    +0.11
    0.03
    379
    +0.11
    0.02
    Negative Logits
    xual
    -0.87
    éĹĺ
    -0.73
    DragonMagazine
    -0.69
    20439
    -0.68
    vier
    -0.65
    skirts
    -0.65
    ograp
    -0.65
    bush
    -0.65
    bread
    -0.64
    hower
    -0.64
    POSITIVE LOGITS
     coordinator
    0.88
     linemen
    0.87
     lineman
    0.87
     tackle
    0.82
     prowess
    0.79
     end
    0.74
     ends
    0.74
     backfield
    0.73
     rebound
    0.72
     misc
    0.72
    Activations Density 0.145%

    No Known Activations