© 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. 0-RES-JB
    11. 22263
    Prev
    Next
    INDEX
    Explanations

    mention of artists or artistic work

    oai_token-act-pair · gpt-3.5-turbo

    references to artists and their roles or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enaries
    -0.76
    angs
    -0.73
    aults
    -0.71
    Vs
    -0.70
    20439
    -0.68
    riage
    -0.65
    Training
    -0.64
    ests
    -0.63
     deployments
    -0.63
    MQ
    -0.62
    POSITIVE LOGITS
     artist
    3.75
     Artist
    2.88
    artist
    2.86
     artists
    2.63
    Artist
    2.63
     Artists
    2.29
     painter
    2.08
     musician
    1.89
     photographer
    1.78
     art
    1.72
    Activations Density 0.017%

    No Known Activations