© 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 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. 2070
    Prev
    Next
    INDEX
    Explanations

    occupations and roles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    professions or roles related to individuals mentioned in the text

    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
    yss
    -0.67
     everlasting
    -0.62
    ENGTH
    -0.61
    rawdownloadcloneembedreportprint
    -0.60
    OHN
    -0.59
    ãĤ¢ãĥ«
    -0.58
    imm
    -0.58
    Motion
    -0.57
    artment
    -0.57
     deletion
    -0.56
    POSITIVE LOGITS
     extraord
    1.00
    culosis
    0.82
    esses
    0.77
     laureate
    0.73
    rors
    0.72
     specializing
    0.71
    ess
    0.64
    nsics
    0.61
    aire
    0.61
     frequ
    0.60
    Activations Density 0.258%

    No Known Activations