© 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. 8-RES-JB
    11. 7927
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "McG" with varying activations, potentially indicating a focus on this specific individual

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "McG" in various contexts

    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
     Gemini
    -0.74
    éĹĺ
    -0.73
    PsyNetMessage
    -0.72
     Reloaded
    -0.68
     lapse
    -0.67
    izations
    -0.65
     CBI
    -0.64
     victim
    -0.64
     juvenile
    -0.64
    ãĥ¼ãĤ¯
    -0.63
    POSITIVE LOGITS
    owan
    1.19
    raw
    1.00
    ruff
    0.97
    inness
    0.94
    REG
    0.92
    arrett
    0.92
    arty
    0.91
    lean
    0.90
    arry
    0.89
    intosh
    0.89
    Activations Density 0.022%

    No Known Activations