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. 8820
    Prev
    Next
    INDEX
    Explanations

    phrases related to revealing or discovering something through investigation or examination

    oai_token-act-pair · gpt-3.5-turbo

    statements that reveal findings or results from observations or analyses

    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
     Shutterstock
    -0.67
    hattan
    -0.66
    anwhile
    -0.66
    cius
    -0.65
    ula
    -0.65
    charge
    -0.61
     onstage
    -0.59
    untary
    -0.58
    nai
    -0.58
    eros
    -0.58
    POSITIVE LOGITS
     similarities
    0.88
     clearly
    0.85
     unmist
    0.81
    WER
    0.80
     none
    0.79
     plenty
    0.78
     nothing
    0.77
     remarkably
    0.76
     numerous
    0.74
     inconsistencies
    0.74
    Activations Density 0.276%

    No Known Activations