© 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. 21108
    Prev
    Next
    INDEX
    Explanations

    specific locations mentioned in texts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific routes or pathways

    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
    uster
    -0.89
    luaj
    -0.86
    usters
    -0.72
    oice
    -0.71
    arden
    -0.70
    endi
    -0.65
    ternity
    -0.64
    untu
    -0.64
    ukes
    -0.63
    iaries
    -0.62
    POSITIVE LOGITS
     routes
    1.10
    finding
    1.06
    Route
    1.04
     route
    0.99
    route
    0.97
    WAYS
    0.90
    finder
    0.88
     routed
    0.84
    WAY
    0.81
     travers
    0.80
    Activations Density 0.048%

    No Known Activations