© 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. 8-RES-JB
    11. 4564
    Prev
    Next
    INDEX
    Explanations

    references to various body hair-related terms, including hairstyles, beards, mustaches, and hair density

    oai_token-act-pair · gpt-3.5-turbo

    references to hair in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lans
    -0.72
    PsyNetMessage
    -0.72
    éĹĺ
    -0.71
    iazep
    -0.69
     Encounter
    -0.67
    ENTION
    -0.64
     Starship
    -0.64
    ukong
    -0.64
     sidx
    -0.63
     Expend
    -0.63
    POSITIVE LOGITS
    pins
    1.21
    pin
    1.11
    dress
    1.11
    bread
    1.10
     foll
    1.06
    pieces
    1.04
    beard
    1.02
     hair
    1.01
    less
    1.01
    line
    0.98
    Activations Density 0.046%

    No Known Activations