© 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. 13145
    Prev
    Next
    INDEX
    Explanations

    proper nouns/geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    locations mentioned in the context of various events or news

    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
    elta
    -0.88
    iously
    -0.75
    manac
    -0.73
    format
    -0.73
    aga
    -0.72
    clude
    -0.72
    efe
    -0.69
    undo
    -0.69
    pac
    -0.67
    Recipe
    -0.67
    POSITIVE LOGITS
     meanwhile
    1.36
     where
    1.36
    where
    1.07
     however
    1.02
     there
    0.92
     wherein
    0.91
     whence
    0.86
     moreover
    0.85
     which
    0.84
     whereby
    0.82
    Activations Density 0.176%

    No Known Activations