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

    Neuronpedia

    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. 16006
    Prev
    Next
    INDEX
    Explanations

    specific phrases that include the words "face-to-face"

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing face-to-face interactions or conflicts

    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
     Cec
    -0.80
     gears
    -0.59
     Zi
    -0.58
     Typhoon
    -0.58
     squid
    -0.56
     Bottom
    -0.56
     OK
    -0.56
     fate
    -0.55
     Aires
    -0.55
     Sanct
    -0.54
    POSITIVE LOGITS
    seeking
    0.93
    offs
    0.89
    off
    0.85
    based
    0.83
    of
    0.83
    raising
    0.81
    offer
    0.81
    itiveness
    0.81
    to
    0.80
    seekers
    0.80
    Activations Density 0.075%

    No Known Activations