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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16822
    Prev
    Next
    INDEX
    Explanations

    words related to academic subjects and professions, such as sciences, economics, and law

    oai_token-act-pair · gpt-3.5-turbo

    references to professional and technical fields or careers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unmarked
    -0.69
     TAMADRA
    -0.67
    fen
    -0.64
    lease
    -0.64
    assian
    -0.63
    dfx
    -0.63
    hani
    -0.63
    ãĥ¼ãĥ³
    -0.63
     unpop
    -0.62
    nen
    -0.62
    POSITIVE LOGITS
    rities
    0.75
    enment
    0.69
     alike
    0.67
    ivals
    0.67
     sciences
    0.65
    STEM
    0.64
     Occupations
    0.64
     constructs
    0.63
     specializing
    0.63
     academics
    0.60
    Activations Density 1.625%

    No Known Activations