© 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. 722
    Prev
    Next
    INDEX
    Explanations

    evaluative statements regarding performance and decisions

    oai_token-act-pair · gpt-3.5-turbo

    positive evaluations or expressions of approval

    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
     Feminist
    -0.79
     exting
    -0.74
    theless
    -0.73
     Shutterstock
    -0.73
    FORE
    -0.69
     Soros
    -0.69
     bourgeois
    -0.68
     Profit
    -0.67
    arest
    -0.67
    NOW
    -0.67
    POSITIVE LOGITS
    Coach
    1.30
     Coach
    1.23
     guys
    1.22
     offensively
    1.08
     Guys
    1.08
     [
    0.98
     coaches
    0.98
     defensively
    0.95
     scrimmage
    0.94
     LeBron
    0.92
    Activations Density 0.483%

    No Known Activations