© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6225
    Prev
    Next
    INDEX
    Explanations

    mentions of names and surnames starting with "Mc"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the prefix "Mc."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unprotected
    -0.79
     Gemini
    -0.78
    ãĥĥãĥĪ
    -0.72
    ãĥ³ãĤ¸
    -0.70
     deaf
    -0.69
    ãĥ¼ãĥĨ
    -0.69
     CBI
    -0.68
     Fract
    -0.64
     ACS
    -0.64
     Atom
    -0.63
    POSITIVE LOGITS
    intosh
    1.40
    Afee
    1.32
    donald
    1.18
    Leod
    1.15
    artney
    1.14
    Connell
    1.09
    Donald
    1.08
    owan
    1.04
    Lean
    1.02
    arthy
    1.00
    Activations Density 0.015%

    No Known Activations