© 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. 10-RES-JB
    11. 7261
    Prev
    Next
    INDEX
    Explanations

    sections related to health and dietary concerns

    oai_token-act-pair · gpt-3.5-turbo

    issues related to health and nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UNCLASSIFIED
    -0.99
     organis
    -0.85
    Dialogue
    -0.82
     continuity
    -0.76
    emort
    -0.75
     Honour
    -0.74
    ileaks
    -0.73
     Dialogue
    -0.72
     [*]
    -0.72
    endar
    -0.70
    POSITIVE LOGITS
     poop
    1.04
    utterstock
    0.99
     pesky
    0.92
     carbs
    0.91
     scientifically
    0.89
     dehyd
    0.89
     adorable
    0.89
     calorie
    0.88
     caffeine
    0.88
     veggies
    0.88
    Activations Density 0.697%

    No Known Activations