© 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. 1-RES-JB
    11. 6760
    Prev
    Next
    INDEX
    Explanations

    mentions of the person "Musk" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of Elon Musk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ×Ļ
    -0.76
    lihood
    -0.73
    WT
    -0.72
    VI
    -0.72
    inals
    -0.69
     Veronica
    -0.66
     Columb
    -0.64
    YN
    -0.64
     Chandra
    -0.63
     Taiwanese
    -0.63
    POSITIVE LOGITS
     Musk
    1.28
    querque
    0.97
    achev
    0.94
    uria
    0.93
    rats
    0.87
    igr
    0.86
    wagen
    0.86
    rament
    0.83
    hetamine
    0.81
    daq
    0.81
    Activations Density 0.011%

    No Known Activations