© 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. 2-RES-JB
    11. 538
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases describing groups of people or objects

    oai_token-act-pair · gpt-3.5-turbo

    the double dash punctuation "--"

    oai_token-act-pair · gpt-4-turbo

    hyphens or dashes used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protective
    -0.74
     discern
    -0.71
    uers
    -0.68
     grave
    -0.68
    othes
    -0.67
     precaution
    -0.65
    ously
    -0.64
     womb
    -0.64
     iceberg
    -0.63
     heart
    -0.63
    POSITIVE LOGITS
    lance
    0.95
    jobs
    0.91
    fuck
    0.91
    _-
    0.88
    something
    0.84
    release
    0.84
    slave
    0.82
    submit
    0.82
    [[
    0.82
    micro
    0.82
    Activations Density 0.011%

    No Known Activations