Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20957
    Prev
    Next
    INDEX
    Explanations

    phrases related to faces or facial features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to facial recognition and facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extremes
    -0.70
     grandson
    -0.68
     Seas
    -0.68
     breath
    -0.68
     Sawyer
    -0.65
     mate
    -0.64
     Polar
    -0.63
     Salvation
    -0.63
     niece
    -0.62
     grandfather
    -0.62
    POSITIVE LOGITS
    ilitation
    1.36
    ulty
    1.27
    etime
    1.24
    eless
    1.19
    ilit
    1.17
    ep
    1.10
    ility
    1.06
    sim
    1.06
    ework
    1.05
    ilitating
    1.04
    Activations Density 0.042%

    No Known Activations