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. 7-RES-JB
    6. 22182
    Prev
    Next
    INDEX
    Explanations

    mentions of declining to comment on a topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "declined to comment."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    corn
    -0.71
     Finch
    -0.69
    tail
    -0.67
    locked
    -0.66
    friend
    -0.64
    nic
    -0.63
    rip
    -0.63
    course
    -0.62
    bey
    -0.62
    eries
    -0.60
    POSITIVE LOGITS
    ariat
    0.97
     specifics
    0.86
     directly
    0.77
    onym
    0.76
     substant
    0.76
     acknow
    0.75
     publicly
    0.75
     anonymously
    0.75
    ature
    0.74
    amera
    0.73
    Activations Density 0.025%

    No Known Activations