© 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. 7-RES-JB
    11. 21144
    Prev
    Next
    INDEX
    Explanations

    words related to faces or facial features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to facial features or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Breed
    -0.71
     extremes
    -0.70
     Seas
    -0.70
     Slug
    -0.68
     ASC
    -0.67
     grandfather
    -0.67
     Fried
    -0.66
     breath
    -0.66
     sands
    -0.65
     Polar
    -0.65
    POSITIVE LOGITS
    ulty
    1.23
    ilitation
    1.23
    eless
    1.13
    ilit
    1.11
    etime
    1.09
    ility
    1.08
    sim
    1.05
    ilities
    1.04
    ep
    1.03
    ework
    0.99
    Activations Density 0.034%

    No Known Activations