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. 14760
    Prev
    Next
    INDEX
    Explanations

    sports-related activities such as making saves, scoring points, and shooting goals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of punctuation and numerical indicators in the text

    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
    Ń·
    -0.91
    swer
    -0.76
    istani
    -0.72
    ensibly
    -0.69
     legally
    -0.68
     popul
    -0.67
    ataka
    -0.66
    onym
    -0.66
     answ
    -0.66
     ç¥ŀ
    -0.66
    POSITIVE LOGITS
    Fresh
    0.89
    Outside
    0.87
    Late
    0.87
    Heat
    0.85
    Ble
    0.84
    Kenn
    0.83
    WHAT
    0.83
    Land
    0.82
    Players
    0.82
    Tra
    0.82
    Activations Density 0.210%

    No Known Activations