© 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. 10-RES-JB
    11. 14090
    Prev
    Next
    INDEX
    Explanations

    words related to American football defensive positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defensive players in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    krit
    -0.74
    Deal
    -0.73
     Gutenberg
    -0.71
    ichen
    -0.69
    bourg
    -0.69
    itious
    -0.68
     Unch
    -0.68
    iless
    -0.67
    olen
    -0.66
    isted
    -0.66
    POSITIVE LOGITS
     linemen
    1.16
     lineman
    1.14
     coordinator
    1.08
     backfield
    0.97
     coordin
    0.95
     tackle
    0.89
     Coordinator
    0.83
     midfield
    0.82
     backs
    0.78
     minded
    0.77
    Activations Density 0.026%

    No Known Activations