© 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. 9-RES-JB
    11. 4260
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic locations and industrial sectors

    oai_token-act-pair · gpt-3.5-turbo
    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
    warn
    -0.68
    summary
    -0.65
     thanking
    -0.64
     Explan
    -0.64
     commented
    -0.63
    recomm
    -0.63
     quoting
    -0.62
    aution
    -0.62
    review
    -0.62
     Investigator
    -0.61
    POSITIVE LOGITS
     hybrids
    0.77
     empires
    0.76
     kingdoms
    0.74
     suburbs
    0.72
     hegemony
    0.70
     coasts
    0.70
     fashionable
    0.69
     skysc
    0.69
     industrialized
    0.69
     stagn
    0.68
    Activations Density 1.009%

    No Known Activations