© 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. 17104
    Prev
    Next
    INDEX
    Explanations

    mentions of artistic disciplines such as poetry, painting, sculpture, and music

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of art and their creators

    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
    null
    -0.53
    ilee
    -0.52
    itent
    -0.51
    Ô
    -0.50
     MIA
    -0.50
     hindsight
    -0.50
    delete
    -0.48
    Fax
    -0.48
    ror
    -0.48
     Removed
    -0.48
    POSITIVE LOGITS
     respectively
    1.02
     apiece
    0.98
     collectively
    0.82
     each
    0.71
     together
    0.66
     Together
    0.65
    each
    0.63
     respective
    0.63
    Together
    0.61
     unified
    0.61
    Activations Density 1.327%

    No Known Activations