© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 23770
    Prev
    Next
    INDEX
    Explanations

    numeric records or scores related to sports outcomes

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to game scores and records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aly
    -0.79
    igmat
    -0.74
    ei
    -0.73
     Barron
    -0.65
    lene
    -0.63
     Sturgeon
    -0.62
     Scand
    -0.62
    reon
    -0.61
     Canary
    -0.60
     Lis
    -0.60
    POSITIVE LOGITS
     victories
    1.15
     wins
    1.11
     games
    1.07
     points
    0.99
     losses
    0.99
     defeats
    0.97
     playoff
    0.96
    game
    0.89
     victory
    0.87
    GAME
    0.86
    Activations Density 0.072%

    No Known Activations