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. 11-RES-JB
    6. 3077
    Prev
    Next
    INDEX
    Explanations

    pronouns (they, we, she, you) and verbs indicating possession or action related to specific locations or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertisement
    -0.86
    orio
    -0.68
    raft
    -0.63
    bringing
    -0.62
     Horizon
    -0.61
     Boat
    -0.60
     Hacker
    -0.60
     Daniels
    -0.60
    iced
    -0.59
    alion
    -0.58
    POSITIVE LOGITS
     excel
    0.99
     intersect
    0.95
     belong
    0.95
     reside
    0.94
     disagree
    0.93
     congreg
    0.91
     shine
    0.89
     thrive
    0.88
     resided
    0.86
     meets
    0.86
    Activations Density 0.132%

    No Known Activations