Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14033
    Prev
    Next
    INDEX
    Explanations

    comments from online platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of comments in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jugg
    -0.78
     lever
    -0.76
     hust
    -0.72
    ardo
    -0.69
     dodge
    -0.69
     holog
    -0.68
     sergeant
    -0.67
    BUS
    -0.66
     cover
    -0.65
     coron
    -0.64
    POSITIVE LOGITS
    Comments
    3.42
     Comments
    2.93
    Comment
    2.76
     Comment
    2.21
    Tags
    1.68
    comments
    1.62
    comment
    1.51
    Rating
    1.46
     Commentary
    1.38
    Reply
    1.32
    Activations Density 0.040%

    No Known Activations