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. 8921
    Prev
    Next
    INDEX
    Explanations

    instances where the word "ill" appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "this" and variations of "ill."

    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
    lished
    -0.73
     Shapiro
    -0.70
    imov
    -0.64
     bestowed
    -0.63
    ISON
    -0.60
     Petr
    -0.59
     repro
    -0.58
     Cancel
    -0.58
     Pixie
    -0.57
     Chester
    -0.57
    POSITIVE LOGITS
    ohyd
    0.85
    ogether
    0.77
    opot
    0.76
    axis
    0.76
    asty
    0.76
    agra
    0.75
    ewater
    0.74
     Nadu
    0.74
    meal
    0.71
    cture
    0.70
    Activations Density 0.048%

    No Known Activations