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. 7467
    Prev
    Next
    INDEX
    Explanations

    phrases related to perseverance and continuation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to perseverance and ongoing action

    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
    iscons
    -0.68
    orthy
    -0.67
    adem
    -0.67
    esp
    -0.67
    odox
    -0.66
    uci
    -0.65
    aucus
    -0.64
    arton
    -0.64
    iquette
    -0.64
    reement
    -0.62
    POSITIVE LOGITS
     endlessly
    1.21
     until
    1.17
     till
    1.06
    until
    1.03
     cycles
    1.01
     successive
    0.95
     relentlessly
    0.92
     iterations
    0.89
     unanswered
    0.88
     repet
    0.87
    Activations Density 0.599%

    No Known Activations