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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 18614
    Prev
    Next
    INDEX
    Explanations

    the word 'bulge' or related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "bulg" or variations thereof, indicating a focus on the concept of "bulge."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ointed
    -0.69
     Defenders
    -0.64
     faire
    -0.62
    CV
    -0.62
    ECH
    -0.60
     Nex
    -0.59
     Poc
    -0.59
     Settlement
    -0.59
     rounding
    -0.57
     compounded
    -0.57
    POSITIVE LOGITS
    wark
    1.37
    leted
    1.09
    gars
    1.09
    ge
    0.99
    ging
    0.96
    gie
    0.94
    ger
    0.94
    keley
    0.92
    GER
    0.91
    ky
    0.91
    Activations Density 0.062%

    No Known Activations