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. 1-RES-JB
    6. 11988
    Prev
    Next
    INDEX
    Explanations

    phrases related to requesting or providing comments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "comment" or related phrases indicating a lack of response or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.76
    xon
    -0.70
    por
    -0.64
    ãĥ³ãĤ¸
    -0.63
    artifacts
    -0.63
     turf
    -0.62
    locked
    -0.62
    solid
    -0.61
     Mississ
    -0.61
     Cav
    -0.60
    POSITIVE LOGITS
     comment
    1.09
    ariat
    0.98
    Comment
    0.95
     comments
    0.92
     Comment
    0.86
     commenting
    0.84
     commenters
    0.80
    ysis
    0.80
    comments
    0.80
     Comments
    0.76
    Activations Density 0.019%

    No Known Activations