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. 22307
    Prev
    Next
    INDEX
    Explanations

    capital letter 'C' characters with ASCII codes 10 and 7

    oai_token-act-pair · gpt-3.5-turbo

    strong emotional expressions or sentiments

    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
    acebook
    -0.76
    uese
    -0.75
    hement
    -0.72
    ulkan
    -0.72
    utical
    -0.72
    xual
    -0.71
    nesday
    -0.70
    ividual
    -0.69
    ensibly
    -0.68
    abwe
    -0.68
    POSITIVE LOGITS
    Unless
    0.91
    ³³³
    0.87
    Reader
    0.87
    Whether
    0.85
    Rated
    0.83
    If
    0.83
    Anyway
    0.83
    Trivia
    0.83
    Scroll
    0.83
    Advertisement
    0.82
    Activations Density 0.309%

    No Known Activations