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. 7553
    Prev
    Next
    INDEX
    Explanations

    the word "But" as the common thread among the activations

    oai_token-act-pair · gpt-3.5-turbo

    the word "But" and its repeated use to introduce contrasting statements or ideas

    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
    ¯¯¯¯
    -0.63
    ãģ®
    -0.61
    heads
    -0.60
    fell
    -0.60
    ().
    -0.59
     segment
    -0.58
    .","
    -0.57
    pointer
    -0.56
    built
    -0.55
    bound
    -0.54
    POSITIVE LOGITS
    tons
    1.24
    chers
    0.88
     alas
    0.86
    theless
    0.85
    withstanding
    0.82
    romeda
    0.81
    owsky
    0.77
    ts
    0.76
    LER
    0.76
    tif
    0.75
    Activations Density 0.088%

    No Known Activations