© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 2575
    Prev
    Next
    INDEX
    Explanations

    phrases related to labels and ingredients in products

    oai_token-act-pair · gpt-3.5-turbo

    references to drug regulation and labeling issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vantage
    -0.95
    Lenin
    -0.87
    Writ
    -0.78
     secession
    -0.76
    Unity
    -0.75
    ysc
    -0.72
    unity
    -0.71
    ghost
    -0.71
    fuck
    -0.71
     chess
    -0.70
    POSITIVE LOGITS
     FDA
    1.63
     manufacturers
    1.37
     additives
    1.37
     marketed
    1.35
     products
    1.31
     pharmaceutical
    1.29
     adul
    1.24
     glyphosate
    1.23
     chemicals
    1.23
     contaminants
    1.22
    Activations Density 0.881%

    No Known Activations