© 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. 1-RES-JB
    11. 20240
    Prev
    Next
    INDEX
    Explanations

    terms related to a medical condition called "trimethylaminuria."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "trimethyline."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.73
     Guilty
    -0.67
     Pharm
    -0.67
     Sioux
    -0.66
     Nations
    -0.66
     Furious
    -0.65
     States
    -0.65
     Bever
    -0.65
    cause
    -0.64
     Correspond
    -0.64
    POSITIVE LOGITS
     trim
    1.15
    ethy
    1.13
    ming
    1.12
     trimmed
    1.03
    ahime
    0.92
    aditional
    0.89
     newcom
    0.88
    inished
    0.87
    ¥ŀ
    0.84
     guiActiveUn
    0.83
    Activations Density 0.007%

    No Known Activations