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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 11939
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating a large difference

    oai_token-act-pair · gpt-3.5-turbo

    extreme degrees of comparison or emphasis in statements

    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
    emis
    -0.84
    icks
    -0.74
    ription
    -0.69
    ysis
    -0.69
     Peel
    -0.69
     Picks
    -0.68
    ortium
    -0.67
    piracy
    -0.67
    ettings
    -0.66
    olor
    -0.65
    POSITIVE LOGITS
    thing
    0.91
    fetched
    0.87
     enough
    0.85
    med
    0.80
     Enough
    0.78
    aday
    0.73
    enough
    0.70
    itud
    0.69
    Range
    0.69
    far
    0.67
    Activations Density 0.028%

    No Known Activations