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. 3-RES-JB
    6. 14620
    Prev
    Next
    INDEX
    Explanations

    timestamps or numbers in a certain format

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data, particularly associated with votes or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istical
    -0.77
    arent
    -0.76
    istically
    -0.74
     Dull
    -0.74
    ggies
    -0.72
    ional
    -0.71
     splash
    -0.67
     Dare
    -0.66
    ioned
    -0.65
    ategic
    -0.65
    POSITIVE LOGITS
    09
    0.89
    089
    0.83
    088
    0.83
    793
    0.79
    08
    0.78
    052
    0.78
    090
    0.76
    06
    0.76
    ¢
    0.76
    059
    0.75
    Activations Density 0.019%

    No Known Activations