© 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. 8-RES-JB
    11. 20361
    Prev
    Next
    INDEX
    Explanations

    locations named "York"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "York."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.78
    SPONSORED
    -0.76
    cedes
    -0.72
    cius
    -0.69
    aeda
    -0.69
    odcast
    -0.68
    ña
    -0.61
    mble
    -0.59
    Oracle
    -0.59
    advertisement
    -0.58
    POSITIVE LOGITS
    town
    1.29
    dale
    1.00
    bean
    0.89
     Rite
    0.89
     Region
    0.88
    ville
    0.87
     City
    0.86
    urst
    0.85
    burgh
    0.84
    oman
    0.83
    Activations Density 0.050%

    No Known Activations