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. 21984
    Prev
    Next
    INDEX
    Explanations

    references to things related to multiple or many

    oai_token-act-pair · gpt-3.5-turbo

    references to multi-year contracts or agreements

    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
    UTION
    -0.75
     rall
    -0.73
     Sketch
    -0.69
     Wonderland
    -0.68
     CPC
    -0.68
     silence
    -0.66
    IONS
    -0.65
     Tol
    -0.65
     Gors
    -0.65
     Bauer
    -0.64
    POSITIVE LOGITS
    ples
    1.42
    player
    1.00
    employ
    0.96
    platform
    0.95
    agency
    0.94
    standard
    0.90
    ply
    0.90
    unit
    0.89
    pled
    0.89
    icult
    0.89
    Activations Density 0.017%

    No Known Activations