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. 1-RES-JB
    6. 12015
    Prev
    Next
    INDEX
    Explanations

    words related to strategic planning or actions taken to achieve a specific goal

    oai_token-act-pair · gpt-3.5-turbo

    references to various strategies, particularly in contexts related to problem-solving or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.73
    oak
    -0.71
     Brotherhood
    -0.71
    export
    -0.66
    rd
    -0.63
    ONT
    -0.63
    gl
    -0.63
    coming
    -0.62
    whelming
    -0.62
    bearing
    -0.62
    POSITIVE LOGITS
     strategies
    1.30
     Strategies
    1.06
     strategy
    1.02
    ategy
    1.00
     lawy
    0.90
     tactics
    0.86
     strateg
    0.81
     reperto
    0.80
    ategic
    0.79
     Strategy
    0.78
    Activations Density 0.006%

    No Known Activations