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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 3274
    Prev
    Next
    INDEX
    Explanations

    references to written communication in the form of letters

    oai_token-act-pair · gpt-3.5-turbo

    references to letters or written correspondence

    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
    AMD
    -0.69
    run
    -0.66
    cosystem
    -0.65
    imate
    -0.65
    stable
    -0.65
    ¥µ
    -0.64
    tackle
    -0.62
    mob
    -0.62
     Grab
    -0.62
    moderate
    -0.61
    POSITIVE LOGITS
     letters
    3.90
     Letters
    2.78
     letter
    2.62
    letters
    2.33
    letter
    2.16
    Letter
    2.10
     Letter
    2.09
     correspondence
    1.82
     memos
    1.57
     emails
    1.54
    Activations Density 0.019%

    No Known Activations