© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 12455
    Prev
    Next
    INDEX
    Explanations

    specific cell receptors in the body

    oai_token-act-pair · gpt-3.5-turbo

    references to biological receptors and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alach
    -0.78
    swe
    -0.72
     Span
    -0.71
    cean
    -0.69
     Chau
    -0.69
    mosp
    -0.67
    iday
    -0.65
     enterprise
    -0.65
    cott
    -0.64
    ippi
    -0.63
    POSITIVE LOGITS
     receptors
    3.20
     receptor
    3.17
     agon
    1.62
     cannabinoid
    1.61
     antibodies
    1.54
    ceptor
    1.43
     antibody
    1.38
    agonist
    1.32
     antagonists
    1.29
     antagonist
    1.27
    Activations Density 0.044%

    No Known Activations