© 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. 6-RES-JB
    11. 4988
    Prev
    Next
    INDEX
    Explanations

    references to blonde individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to hair color, particularly blonde and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMS
    -0.92
     Flavoring
    -0.82
    inventoryQuantity
    -0.79
    afort
    -0.75
    atically
    -0.74
     Surv
    -0.73
    ciplinary
    -0.71
    aves
    -0.71
    iazep
    -0.71
    abilities
    -0.71
    POSITIVE LOGITS
     wig
    1.44
    haired
    1.28
     blond
    1.16
     hairst
    1.03
     hair
    1.03
     blonde
    1.01
     scalp
    0.93
    ness
    0.92
     bald
    0.91
    beard
    0.89
    Activations Density 0.037%

    No Known Activations