© 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. 0-RES-JB
    11. 19922
    Prev
    Next
    INDEX
    Explanations

    names of political figures, specifically with the ending "oglu"

    oai_token-act-pair · gpt-3.5-turbo

    words that describe kitschy or cheesy elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advocate
    -0.60
     Twin
    -0.59
     VERS
    -0.57
     reve
    -0.57
     Warren
    -0.57
     pas
    -0.56
     tech
    -0.56
     technology
    -0.56
     EDIT
    -0.56
     Repl
    -0.55
    POSITIVE LOGITS
    chy
    4.84
    ching
    1.13
    ches
    1.09
    itsch
    1.05
    ched
    0.95
    cham
    0.93
    oglu
    0.90
    vous
    0.89
    icular
    0.89
    merce
    0.87
    Activations Density 0.020%

    No Known Activations