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. 1-RES-JB
    6. 19431
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, particularly the city of Raleigh, North Carolina, and educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and terms associated with geographical or notable entities

    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
    uchin
    -0.85
    berman
    -0.80
    ocene
    -0.78
    arers
    -0.78
    ebook
    -0.75
    ramid
    -0.75
    atography
    -0.71
    otom
    -0.71
    quer
    -0.70
    lasses
    -0.70
    POSITIVE LOGITS
     Providence
    1.49
     mosqu
    0.89
     Timbers
    0.80
     Garden
    0.74
     Almighty
    0.74
    mouth
    0.73
    idence
    0.73
    esses
    0.72
     Ascend
    0.72
     Incarn
    0.69
    Activations Density 0.009%

    No Known Activations