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. 23754
    Prev
    Next
    INDEX
    Explanations

    Specific mentions of the last name "McClure."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities associated with the name "McCl."

    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
    oven
    -0.83
     Weinstein
    -0.79
     fermented
    -0.76
    abus
    -0.74
     Fry
    -0.74
     ve
    -0.71
     sweets
    -0.71
     Wilde
    -0.71
    mone
    -0.71
     Miche
    -0.71
    POSITIVE LOGITS
     McCl
    1.88
     CM
    1.44
     Atl
    1.39
    atl
    1.39
     Kl
    1.35
    orth
    1.27
     ATL
    1.25
    Atl
    1.21
     PL
    1.20
    CM
    1.19
    Activations Density 0.054%

    No Known Activations