© 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. 9-RES-JB
    11. 19913
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially related to locations and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places, events, and significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    jriwal
    -0.58
    ibliography
    -0.58
    rower
    -0.57
    zsche
    -0.57
    cknowled
    -0.56
    onym
    -0.56
    genre
    -0.56
     thing
    -0.54
    job
    -0.54
    eanor
    -0.53
    POSITIVE LOGITS
    's
    0.77
    ®,
    0.74
     Holdings
    0.71
     Boulevard
    0.64
     Airlines
    0.63
     fame
    0.62
     Studios
    0.62
     Junction
    0.62
    *.
    0.61
     whereby
    0.61
    Activations Density 0.600%

    No Known Activations