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. 63
    Prev
    Next
    INDEX
    Explanations

    instances of the word "scoop" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scoop" and related variations

    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
    lihood
    -0.75
    idency
    -0.72
     livest
    -0.71
    audi
    -0.66
    usable
    -0.64
    repeat
    -0.64
    senal
    -0.63
    uctor
    -0.62
     pathways
    -0.62
     diligence
    -0.62
    POSITIVE LOGITS
     scoop
    1.12
    iest
    0.95
    iness
    0.92
    sheet
    0.88
    oops
    0.86
    fall
    0.85
    hest
    0.84
    sters
    0.84
    sheets
    0.80
    ing
    0.77
    Activations Density 0.019%

    No Known Activations