© 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. 14296
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific proper noun, "Drudge"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Dr.udge" or variations of it in the text

    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
    ccording
    -0.83
    spect
    -0.65
    fig
    -0.63
    ervation
    -0.61
     burg
    -0.59
    ensive
    -0.59
     likelihood
    -0.58
    occup
    -0.58
    practice
    -0.57
     pronounced
    -0.57
    POSITIVE LOGITS
    udge
    1.47
    weed
    0.80
    hog
    0.73
     Whedon
    0.72
    ango
    0.72
    elta
    0.70
    undle
    0.70
    reau
    0.69
    hower
    0.69
    ragon
    0.69
    Activations Density 0.007%

    No Known Activations