© 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. 0-RES-JB
    11. 16492
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals holding specific job titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lex
    -0.77
     squat
    -0.70
     squares
    -0.69
    mop
    -0.66
    Ê
    -0.64
     glyph
    -0.64
    alty
    -0.63
     squats
    -0.63
    hip
    -0.62
    Ò
    -0.61
    POSITIVE LOGITS
     Director
    3.59
    Director
    2.87
     director
    2.55
     Directors
    2.32
    director
    2.19
     directors
    1.90
     Coordinator
    1.74
     Administrator
    1.74
     Secretary
    1.73
     Superintendent
    1.71
    Activations Density 0.010%

    No Known Activations