© 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. 9-RES-JB
    11. 1319
    Prev
    Next
    INDEX
    Explanations

    words related to climbing or high altitudes

    oai_token-act-pair · gpt-3.5-turbo

    words related to roles or occupations, specifically those ending in various suffixes typically associated with job titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¯
    -0.67
    ellar
    -0.67
    ENS
    -0.64
    ISON
    -0.64
    angan
    -0.62
    ENSE
    -0.62
    Spons
    -0.62
    ij
    -0.61
    ij士
    -0.61
    herty
    -0.61
    POSITIVE LOGITS
     extraord
    1.50
    esses
    0.98
     beware
    0.95
    ess
    0.88
     who
    0.86
    gery
    0.86
    hip
    0.81
     clad
    0.80
     canoe
    0.77
    doms
    0.74
    Activations Density 0.230%

    No Known Activations