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. 349
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "McG" with varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    the name "McG," indicating a focus on references to a specific person or entity associated with that name

    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
     Tunis
    -0.64
    odes
    -0.64
     serv
    -0.64
     colon
    -0.64
     babe
    -0.63
     violin
    -0.61
    Joined
    -0.61
     Zeal
    -0.60
     brace
    -0.60
    eer
    -0.60
    POSITIVE LOGITS
     McG
    3.94
    Mc
    1.72
     McM
    1.58
     McGr
    1.57
     McH
    1.57
     McGu
    1.51
     McGee
    1.48
     McF
    1.48
     McCl
    1.42
     McK
    1.37
    Activations Density 0.012%

    No Known Activations