© 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. 8-RES-JB
    11. 3852
    Prev
    Next
    INDEX
    Explanations

    names of locations or streets

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations or place names

    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
    dyl
    -0.82
    PDATE
    -0.76
    ggle
    -0.75
    glomer
    -0.71
     uncond
    -0.71
    hran
    -0.70
     sympathetic
    -0.69
     carbohyd
    -0.69
    agonists
    -0.69
    accompan
    -0.69
    POSITIVE LOGITS
     County
    1.46
     Township
    1.46
     Manor
    1.37
     Creek
    1.35
     Falls
    1.31
     Heights
    1.30
    stown
    1.29
     Avenue
    1.29
     Hills
    1.28
     Valley
    1.27
    Activations Density 0.248%

    No Known Activations