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. 20576
    Prev
    Next
    INDEX
    Explanations

    the symbol "âĢ" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in programming or markup

    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
    iewicz
    -0.81
     Ukrain
    -0.76
    creen
    -0.71
     Ferguson
    -0.67
     Libyan
    -0.66
     raft
    -0.65
     distraction
    -0.64
     Drawn
    -0.64
     Hitman
    -0.63
     Roc
    -0.63
    POSITIVE LOGITS
    ł
    1.16
    IJ
    1.10
    ª
    1.07
    ¹
    1.04
    ij
    1.01
    į
    1.00
    Ĵ
    0.99
    ı
    0.97
    £
    0.95
    Ķ
    0.95
    Activations Density 0.172%

    No Known Activations