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. 18223
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "Her" or "Herb"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Her."

    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
     Lomb
    -0.62
     numbered
    -0.62
     matters
    -0.60
     matter
    -0.59
     rehe
    -0.59
     Paste
    -0.58
     scares
    -0.58
     together
    -0.57
     Zin
    -0.56
     psi
    -0.56
    POSITIVE LOGITS
    itage
    1.51
    cule
    1.48
     Majesty
    1.44
    mit
    1.37
    metic
    1.36
    acl
    1.24
    oes
    1.22
    cules
    1.22
    acles
    1.20
    ding
    1.18
    Activations Density 0.037%

    No Known Activations