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. 4638
    Prev
    Next
    INDEX
    Explanations

    dates in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    periods indicating the end of statements or sentences

    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
     pudding
    -0.85
     fishes
    -0.80
     everywhere
    -0.77
     sauces
    -0.76
     minion
    -0.74
     hats
    -0.72
     necks
    -0.71
     opponent
    -0.71
     instinct
    -0.70
     heav
    -0.70
    POSITIVE LOGITS
     However
    1.01
     Afterwards
    0.99
     Since
    0.96
     Additionally
    0.95
     According
    0.95
     Meanwhile
    0.93
     Previously
    0.92
     Presumably
    0.92
     Alternatively
    0.90
     Similarly
    0.89
    Activations Density 0.521%

    No Known Activations