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. 140
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the character James Bond

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Bond" related to the James Bond franchise

    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
    à
    -0.77
     roasted
    -0.76
     estim
    -0.70
    geon
    -0.68
    ython
    -0.66
     pus
    -0.66
     prin
    -0.65
    tl
    -0.63
     admins
    -0.63
     "%
    -0.62
    POSITIVE LOGITS
     Bond
    3.98
     Bonds
    2.33
     bond
    1.82
     bonds
    1.61
     bonding
    1.49
     Fleming
    1.37
     bonded
    1.26
     Bale
    1.25
     Casino
    1.14
     Hitchcock
    1.13
    Activations Density 0.024%

    No Known Activations