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. 10577
    Prev
    Next
    INDEX
    Explanations

    references to food items, especially those related to chocolate and caramel

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands and types of food products, particularly sweets and snacks

    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
    NN
    -0.70
    ales
    -0.69
    xy
    -0.68
    alt
    -0.67
    ĩ
    -0.67
     Jinping
    -0.66
    lar
    -0.64
    ^^^^
    -0.64
    Builder
    -0.64
    printf
    -0.64
    POSITIVE LOGITS
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.88
    istically
    0.80
    mental
    0.77
     Tasman
    0.76
    istic
    0.76
    amel
    0.73
    pelled
    0.72
    ciation
    0.68
    arette
    0.67
     drib
    0.66
    Activations Density 0.045%

    No Known Activations