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. 18982
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of impact

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "impossible" and "impact."

    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
    creen
    -1.15
    mberg
    -0.77
    wald
    -0.72
    gian
    -0.71
     Seym
    -0.70
    çĦ
    -0.70
     conductor
    -0.70
    mates
    -0.70
     Ribbon
    -0.68
    krit
    -0.67
    POSITIVE LOGITS
    ressive
    1.36
    ulse
    1.36
    ression
    1.31
    ossible
    1.25
    romptu
    1.21
    ractical
    1.20
    ossibly
    1.19
    ossibility
    1.17
    acts
    1.17
    unity
    1.13
    Activations Density 0.020%

    No Known Activations