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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 21696
    Prev
    Next
    INDEX
    Explanations

    keywords related to official written communications or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to official documents or memos

    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
     Supported
    -0.66
    iba
    -0.64
    ield
    -0.64
     Incarn
    -0.64
    Interstitial
    -0.63
     everyday
    -0.62
    strate
    -0.62
    ury
    -0.61
    orthy
    -0.61
     runners
    -0.61
    POSITIVE LOGITS
     memo
    3.80
     memos
    2.63
     memorandum
    2.13
     Mem
    1.42
     letter
    1.41
     document
    1.34
     Memor
    1.32
     directive
    1.27
     dossier
    1.24
     bulletin
    1.23
    Activations Density 0.013%

    No Known Activations