Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1700
    Prev
    Next
    INDEX
    Explanations

    terms related to various professions or fields of expertise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various fields of professional expertise

    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
    selves
    -0.88
     Countries
    -0.81
     Balls
    -0.80
     Characters
    -0.80
     Ones
    -0.80
     Pieces
    -0.78
     Result
    -0.74
     Soldiers
    -0.72
     Winners
    -0.72
     Piece
    -0.72
    POSITIVE LOGITS
     sciences
    1.08
     anthropology
    1.03
     strategist
    1.00
     consulting
    0.97
     sociology
    0.97
     affairs
    0.96
     advisory
    0.96
     psychologist
    0.94
     analytics
    0.94
     ecology
    0.93
    Activations Density 0.289%

    No Known Activations