© 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. 6661
    Prev
    Next
    INDEX
    Explanations

    references to playing musical instruments and sports

    oai_token-act-pair · gpt-3.5-turbo

    references to musical activities and performances

    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
     Canaver
    -0.93
    CNN
    -0.80
    Brexit
    -0.75
     roadmap
    -0.72
    ÄŁ
    -0.72
    bnb
    -0.71
    TPPStreamerBot
    -0.71
    andowski
    -0.70
    xit
    -0.70
     ado
    -0.69
    POSITIVE LOGITS
    arsity
    0.98
     Harlem
    0.94
     prestigious
    0.86
     graduating
    0.85
     collegiate
    0.85
     Junior
    0.85
     Juven
    0.83
     youth
    0.83
     Boys
    0.81
     Commodore
    0.81
    Activations Density 0.483%

    No Known Activations