© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10278
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "iff" with varying levels of importance or related contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Eiffel Tower

    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
    igators
    -0.69
    igator
    -0.66
    igated
    -0.63
    GREEN
    -0.63
    ADVERTISEMENT
    -0.62
     Sham
    -0.61
    ãĥŁ
    -0.60
     Nobel
    -0.60
     Journalism
    -0.59
    ctica
    -0.59
    POSITIVE LOGITS
    iculty
    1.20
    erey
    0.93
    erence
    0.93
    doms
    0.93
    ield
    0.93
    erences
    0.88
    icult
    0.86
    rence
    0.85
    onic
    0.83
    enstein
    0.82
    Activations Density 0.069%

    No Known Activations