Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4793
    Prev
    Next
    INDEX
    Explanations

    descriptions of people's activities and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of people involved in a narrative or event

    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
     wink
    -0.74
    )?
    -0.66
     grit
    -0.66
     pages
    -0.63
     fundament
    -0.63
     aster
    -0.62
     reproduced
    -0.62
     capit
    -0.62
     singular
    -0.61
    rists
    -0.61
    POSITIVE LOGITS
    terday
    0.75
     renov
    0.73
    ercise
    0.71
     mosqu
    0.70
    phrine
    0.69
     holiday
    0.68
    oultry
    0.67
     convoy
    0.67
    uties
    0.67
    due
    0.67
    Activations Density 0.597%

    No Known Activations