© 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. 4-RES-JB
    11. 3650
    Prev
    Next
    INDEX
    Explanations

    phrases related to endocrine hormones and biological processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological processes and hormone regulation

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

    No Comments

    Negative Logits
    awaru
    -0.85
     accur
    -0.77
    rising
    -0.76
    hift
    -0.72
    Mist
    -0.70
    udicrous
    -0.68
     surn
    -0.68
     Franch
    -0.67
     tru
    -0.65
    soDeliveryDate
    -0.65
    POSITIVE LOGITS
     inflammation
    1.05
     lymph
    0.99
     gland
    0.95
    lamm
    0.93
     enzyme
    0.91
     tissue
    0.89
     tissues
    0.89
     dysfunction
    0.88
    ocytes
    0.87
     stimulating
    0.86
    Activations Density 0.110%

    No Known Activations