© 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. 7-RES-JB
    11. 4990
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal settings like courts and trials

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.94
     buoy
    -0.69
     orn
    -0.67
     sparing
    -0.67
     irresist
    -0.65
     lav
    -0.63
     dense
    -0.63
     Ruby
    -0.63
     Wing
    -0.62
     ($)
    -0.62
    POSITIVE LOGITS
    sic
    1.70
    laughs
    1.50
    Laughs
    1.27
    emphasis
    1.19
    âĢ¦)
    1.14
    laughter
    1.04
    ...)
    1.02
    Wednesday
    1.01
    insert
    1.01
    laugh
    0.98
    Activations Density 0.055%

    No Known Activations