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. 15891
    Prev
    Next
    INDEX
    Explanations

    styles or attributes in text, which could relate to various domains such as fashion, design, music, and writing

    oai_token-act-pair · gpt-3.5-turbo

    references to stylistic elements or features

    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
    riel
    -0.75
    minster
    -0.73
    VEN
    -0.70
    azar
    -0.69
     Kira
    -0.68
    leased
    -0.66
    ertodd
    -0.65
     Lauder
    -0.65
    lehem
    -0.65
    worth
    -0.65
    POSITIVE LOGITS
    heet
    0.93
    edo
    0.80
    ologies
    0.79
     sheet
    0.76
     sheets
    0.76
    styles
    0.73
     guiName
    0.69
    ahead
    0.68
    ably
    0.67
    face
    0.67
    Activations Density 0.037%

    No Known Activations