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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 4-RES-JB
    6. 5015
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the design and functionality quality of products

    oai_token-act-pair · gpt-3.5-turbo

    elements related to game design and overall user experience

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

    No Comments

    Negative Logits
    educ
    -0.77
    ym
    -0.75
    icist
    -0.71
    bid
    -0.70
    aire
    -0.69
    education
    -0.69
    zin
    -0.69
    frey
    -0.68
    stad
    -0.68
    stan
    -0.68
    POSITIVE LOGITS
     versatility
    0.94
     simplicity
    0.93
     matte
    0.92
     responsiveness
    0.90
     chrome
    0.89
     midrange
    0.86
     aesthetics
    0.86
     elegance
    0.85
     tremend
    0.85
     quirks
    0.84
    Activations Density 0.969%

    No Known Activations