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

    Neuronpedia

    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. 4-RES-JB
    11. 22630
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the surname "McG" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named McG

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

    No Comments

    Negative Logits
    PsyNetMessage
    -0.84
    terday
    -0.76
     Gemini
    -0.73
    izations
    -0.72
    éĹĺ
    -0.72
    inent
    -0.66
     UE
    -0.63
    isation
    -0.63
     Sector
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.63
    POSITIVE LOGITS
    owan
    0.97
    inness
    0.94
    intosh
    0.93
    ruff
    0.87
    REG
    0.87
     McG
    0.85
    ru
    0.85
    raw
    0.85
    eneg
    0.85
    rowth
    0.85
    Activations Density 0.006%

    No Known Activations