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. 4-RES-JB
    6. 8150
    Prev
    Next
    INDEX
    Explanations

    news articles by recognizing the use of the phrase "According to" followed by a source and some information

    oai_token-act-pair · gpt-3.5-turbo

    instances of citation or attribution in statements

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

    No Comments

    Negative Logits
    ãĥ¥
    -0.82
    phony
    -0.65
    Pont
    -0.64
    stage
    -0.63
    ennial
    -0.62
    enta
    -0.61
    puff
    -0.60
    heartedly
    -0.60
    aval
    -0.59
    away
    -0.59
    POSITIVE LOGITS
     citing
    0.90
     "â̦
    0.80
     although
    0.76
     anecd
    0.73
     quoting
    0.72
     "[
    0.71
    uthor
    0.70
     however
    0.70
     "$
    0.68
     "(
    0.68
    Activations Density 0.171%

    No Known Activations