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. 8704
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "come"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "come" and its variations

    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
    IELD
    -0.64
    nesota
    -0.63
    esa
    -0.63
     Converted
    -0.62
    eer
    -0.61
    ¥µ
    -0.60
    nature
    -0.59
     ASP
    -0.59
    itcher
    -0.58
    elsius
    -0.57
    POSITIVE LOGITS
     forward
    0.95
     undone
    0.94
     forth
    0.93
     together
    0.86
     under
    0.84
    upp
    0.80
     clean
    0.80
    under
    0.80
     knocking
    0.79
     unst
    0.75
    Activations Density 0.051%

    No Known Activations