© 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. 6679
    Prev
    Next
    INDEX
    Explanations

    descriptions of hair attributes and hair treatments

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of hair and its characteristics

    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
    agents
    -0.87
    Disk
    -0.82
    Mission
    -0.82
     feasibility
    -0.77
    MAP
    -0.76
    SQL
    -0.76
     privatization
    -0.75
    VR
    -0.75
     negotiators
    -0.74
     sidx
    -0.73
    POSITIVE LOGITS
     hair
    1.82
     hairst
    1.73
     curls
    1.66
     hairs
    1.56
     curly
    1.52
     Hair
    1.46
     beard
    1.45
     shaved
    1.41
     blond
    1.36
     haircut
    1.36
    Activations Density 0.160%

    No Known Activations