Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19654
    Prev
    Next
    INDEX
    Explanations

    phrases that come after the word "by"

    oai_token-act-pair · gpt-3.5-turbo

    the word "by" in various contexts, indicating authorship or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paren
    -0.79
     manif
    -0.73
    ioned
    -0.68
    mble
    -0.68
    hement
    -0.66
    ij士
    -0.66
     torped
    -0.66
    uality
    -0.64
     pains
    -0.64
    vation
    -0.63
    POSITIVE LOGITS
     virtue
    0.81
    laws
    0.76
    product
    0.76
     guiActive
    0.70
    products
    0.68
     Sponsor
    0.64
     Lets
    0.63
     STATS
    0.62
    pass
    0.61
     Guest
    0.59
    Activations Density 0.056%

    No Known Activations