© 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. 9875
    Prev
    Next
    INDEX
    Explanations

    references to dance performances and physical actions

    oai_token-act-pair · gpt-3.5-turbo

    references to performance and choreography

    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
    isSpecialOrderable
    -0.98
    Miller
    -0.89
    soType
    -0.88
     Wheat
    -0.88
    idges
    -0.86
    ettlement
    -0.85
    keye
    -0.83
     Investor
    -0.81
    pg
    -0.81
     Warranty
    -0.79
    POSITIVE LOGITS
     dancers
    2.55
     dancer
    2.27
     dances
    2.22
     dance
    2.18
     dancing
    2.13
     danced
    2.04
     ballet
    1.96
     Dance
    1.89
     chore
    1.85
     Dancing
    1.78
    Activations Density 0.291%

    No Known Activations