© 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. 12848
    Prev
    Next
    INDEX
    Explanations

    terms related to internal organs, particularly the liver and kidneys

    oai_token-act-pair · gpt-3.5-turbo

    references to liver and kidney health issues

    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
    umar
    -0.71
     Whedon
    -0.71
    âĶģ
    -0.70
    minus
    -0.68
    aganda
    -0.63
    é¾įå¥ij士
    -0.63
     McKenna
    -0.61
    ãģ®éŃĶ
    -0.61
     Samoa
    -0.61
     Chancellor
    -0.60
    POSITIVE LOGITS
    ysis
    0.92
     cir
    0.91
     enzymes
    0.88
     glyc
    0.81
    neys
    0.80
     enzyme
    0.79
     liver
    0.79
    stones
    0.78
    hyde
    0.78
    ney
    0.78
    Activations Density 0.048%

    No Known Activations