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. 0-RES-JB
    6. 7034
    Prev
    Next
    INDEX
    Explanations

    terms related to law and legislation

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to strong emotions or dramatic reactions

    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
    itably
    -0.96
     referen
    -0.89
    acebook
    -0.88
    retty
    -0.87
    escription
    -0.87
    irlf
    -0.81
    ocument
    -0.76
    ividually
    -0.76
    efeated
    -0.76
    mercial
    -0.76
    POSITIVE LOGITS
    NetMessage
    1.02
    CLASSIFIED
    0.95
    WAYS
    0.87
     largeDownload
    0.86
     Lumpur
    0.80
    natureconservancy
    0.80
     toile
    0.76
    namese
    0.76
    SELECT
    0.74
    BILITY
    0.71
    Activations Density 7.941%

    No Known Activations