© 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. 9272
    Prev
    Next
    INDEX
    Explanations

    descriptive terms for visual arts

    oai_token-act-pair · gpt-3.5-turbo

    references to art exhibitions and collections

    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
    amacare
    -1.00
    undown
    -0.87
     HHS
    -0.86
    ghazi
    -0.83
    QB
    -0.81
    VPN
    -0.81
    isSpecialOrderable
    -0.81
     TEST
    -0.79
     Oversight
    -0.78
     SATA
    -0.78
    POSITIVE LOGITS
     paintings
    1.99
     sculpture
    1.92
     artwork
    1.88
     artist
    1.84
     painter
    1.83
     painting
    1.82
     sculptures
    1.81
     mural
    1.79
     art
    1.74
     artistic
    1.73
    Activations Density 0.708%

    No Known Activations