© 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 EvalsExportsAPI 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. 3467
    Prev
    Next
    INDEX
    Explanations

    phrases related to bodily processes and substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bodily substances and their interactions within biological systems

    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
    edIn
    -0.79
    htaking
    -0.79
    thodox
    -0.65
    bernatorial
    -0.65
    DEM
    -0.64
     honorary
    -0.64
    arsity
    -0.64
    ploma
    -0.63
    OSED
    -0.62
     Scout
    -0.62
    POSITIVE LOGITS
     bloodstream
    1.32
     cavity
    1.25
     pores
    1.21
     membranes
    1.15
     tissues
    1.13
     membrane
    1.03
     fluids
    1.01
    osphere
    0.98
     undet
    0.96
     reservoirs
    0.96
    Activations Density 0.183%

    No Known Activations