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. 11-RES-JB
    6. 19718
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs and financial considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to cost analysis and budget considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ctrl
    -0.75
     Psychiat
    -0.73
     Methodist
    -0.73
    ="#
    -0.71
     Dumb
    -0.67
    united
    -0.67
    Girls
    -0.67
    hent
    -0.66
    Lie
    -0.66
    chool
    -0.65
    POSITIVE LOGITS
     profitability
    1.51
     timelines
    1.37
     availability
    1.35
     affordability
    1.34
     costs
    1.33
     feasibility
    1.31
     pricing
    1.30
     cost
    1.27
     throughput
    1.27
     reliability
    1.26
    Activations Density 0.383%

    No Known Activations