Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 17436
    Prev
    Next
    INDEX
    Explanations

    quantitative details related to nutrition or measurement

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to food items and their nutritional content

    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
    print
    -0.72
    otto
    -0.67
    ortment
    -0.64
    alia
    -0.63
    guided
    -0.62
    redo
    -0.62
    gra
    -0.60
    DNA
    -0.60
    cele
    -0.58
    gat
    -0.58
    POSITIVE LOGITS
    osuke
    0.75
     increments
    0.74
    acters
    0.73
     apiece
    0.72
    alion
    0.65
    fen
    0.65
    /$
    0.65
     Bucc
    0.64
     (âĪĴ
    0.64
     Wraith
    0.63
    Activations Density 0.266%

    No Known Activations