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. 17713
    Prev
    Next
    INDEX
    Explanations

    information related to economic indicators, particularly statistics regarding gross domestic product (GDP)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "gross" in various contexts, particularly related to economic indicators

    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
    attled
    -0.79
    ournal
    -0.68
     Buckingham
    -0.68
    chers
    -0.64
     accomp
    -0.63
     therap
    -0.63
    pires
    -0.63
    abies
    -0.61
     Franç
    -0.61
    uberty
    -0.61
    POSITIVE LOGITS
     receipts
    0.90
    gross
    0.86
     gross
    0.84
    es
    0.80
    ewater
    0.79
    cre
    0.78
    hest
    0.78
    ling
    0.70
     disproportion
    0.69
    nih
    0.67
    Activations Density 0.016%

    No Known Activations