© 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. 13669
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the prefix "Mc"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mc" in various contexts

    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
     unprotected
    -0.81
     misunderstood
    -0.75
     ACS
    -0.73
     downt
    -0.67
     therefore
    -0.66
     Acts
    -0.66
     indicative
    -0.63
     show
    -0.62
     deaf
    -0.61
     none
    -0.60
    POSITIVE LOGITS
    Afee
    1.52
    Connell
    1.43
    Leod
    1.39
    Kin
    1.38
    intosh
    1.36
    Lean
    1.34
    Donald
    1.33
    Bride
    1.32
    Donnell
    1.31
    Kay
    1.23
    Activations Density 0.011%

    No Known Activations