© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 21802
    Prev
    Next
    INDEX
    Explanations

    mentions of various body hair types

    oai_token-act-pair · gpt-3.5-turbo

    references to hair and related grooming features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTION
    -0.68
     Encounter
    -0.65
    éĹĺ
    -0.65
    ividual
    -0.65
    ACTED
    -0.63
    eers
    -0.63
     Gutenberg
    -0.63
     Lans
    -0.62
    ukong
    -0.62
    Critical
    -0.62
    POSITIVE LOGITS
    pins
    1.20
    pin
    1.04
     hair
    1.04
     foll
    1.03
    bread
    1.03
    dress
    1.01
    beard
    0.99
    pieces
    0.99
    less
    0.97
    brush
    0.97
    Activations Density 0.033%

    No Known Activations