© 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. 5602
    Prev
    Next
    INDEX
    Explanations

    words related to body organs

    oai_token-act-pair · gpt-3.5-turbo

    references to human anatomy and bodily organs

    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
     Lank
    -0.73
    MER
    -0.73
    channelAvailability
    -0.72
    Hur
    -0.72
    Mah
    -0.68
     Fantasy
    -0.66
     Courage
    -0.66
     Alam
    -0.66
     Sunny
    -0.64
     Wildcats
    -0.64
    POSITIVE LOGITS
     organs
    1.64
    pots
    1.04
     transplant
    1.00
     kidneys
    0.93
    ktop
    0.92
     organ
    0.88
     tissues
    0.85
    rats
    0.84
     eater
    0.83
    puter
    0.80
    Activations Density 0.007%

    No Known Activations