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. 11025
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person named Stein

    oai_token-act-pair · gpt-3.5-turbo

    quotes or reported speech in the text

    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
     monkeys
    -1.05
     Bates
    -0.88
     Cousins
    -0.87
     tyr
    -0.84
     Bangkok
    -0.84
     Bran
    -0.83
    monkey
    -0.83
     Naruto
    -0.82
    amon
    -0.81
    atus
    -0.81
    POSITIVE LOGITS
     Stein
    2.40
    Ste
    2.29
     Ste
    1.94
     STE
    1.75
     ste
    1.62
    STE
    1.58
     Stella
    1.42
     Steele
    1.35
    ste
    1.34
     Steel
    1.31
    Activations Density 0.235%

    No Known Activations