© 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. 4-RES-JB
    11. 17248
    Prev
    Next
    INDEX
    Explanations

    terms related to barbershops and hair-related professions

    oai_token-act-pair · gpt-3.5-turbo

    words relating to professions or roles, especially in the context of service or industry

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

    No Comments

    Negative Logits
     Incarn
    -0.86
    bows
    -0.73
    TPS
    -0.72
     Nato
    -0.70
    FUL
    -0.68
     Ramadan
    -0.66
    00200000
    -0.64
     Jinping
    -0.63
     Reign
    -0.62
    anchester
    -0.61
    POSITIVE LOGITS
     specializing
    0.90
     examiner
    0.87
     operator
    0.85
     negoti
    0.78
     clerk
    0.78
    esses
    0.77
     specialize
    0.77
     technician
    0.76
     operators
    0.75
    agent
    0.75
    Activations Density 0.474%

    No Known Activations