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. 0-RES-JB
    6. 3682
    Prev
    Next
    INDEX
    Explanations

    names of historical or fictional figures, particularly those associated with religious or cultural significance

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to historical or notable figures

    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
     Roosevelt
    -0.95
     ADV
    -0.81
     Cogn
    -0.81
     Fram
    -0.78
     Candy
    -0.77
     Carmen
    -0.73
    ogn
    -0.72
    artisan
    -0.70
     Okinawa
    -0.69
     Guam
    -0.69
    POSITIVE LOGITS
     Moses
    2.25
     Bolt
    1.83
     Isaac
    1.60
    bolt
    1.33
     Gibbs
    1.31
     bolt
    1.27
     bolts
    1.18
     Fir
    1.17
    bane
    1.15
    Isa
    1.12
    Activations Density 0.032%

    No Known Activations