© 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. 11-RES-JB
    11. 21175
    Prev
    Next
    INDEX
    Explanations

    expressions related to social interactions and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    comma usage in sentences with contrasting ideas or clauses

    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
    tains
    -0.88
    itational
    -0.74
    ãĥīãĥ©
    -0.68
    nergy
    -0.67
    qqa
    -0.66
    ãĥ¯
    -0.65
    tesy
    -0.63
    cellence
    -0.63
    luence
    -0.62
    eatures
    -0.62
    POSITIVE LOGITS
     fearing
    1.31
     afraid
    1.14
     worried
    1.03
     preferring
    1.01
     ashamed
    1.00
     believing
    0.99
     realizing
    0.98
     wondering
    0.98
     feared
    0.97
     thinking
    0.97
    Activations Density 0.396%

    No Known Activations