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. 8-RES-JB
    6. 1411
    Prev
    Next
    INDEX
    Explanations

    sentences that end with punctuation marks, especially periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express conclusions or clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¬
    -0.75
     pione
    -0.69
     teasp
    -0.69
    ascus
    -0.68
    arbon
    -0.68
     strap
    -0.67
     exting
    -0.66
     superiority
    -0.66
     redes
    -0.65
    ¶ħ
    -0.64
    POSITIVE LOGITS
     Sometimes
    1.40
     Examples
    1.35
     Often
    1.27
     Usually
    1.17
     Typically
    1.15
     Particularly
    1.11
     Occasionally
    1.10
     Some
    1.08
     Especially
    1.08
     Flavoring
    1.07
    Activations Density 0.676%

    No Known Activations