© 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. 4-RES-JB
    11. 22188
    Prev
    Next
    INDEX
    Explanations

    references to the action of being escorted or escorting someone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "escort" and its variations, indicating activities related to guiding or accompanying individuals

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

    No Comments

    Negative Logits
    ulz
    -0.69
    ãĤ©
    -0.68
    brance
    -0.67
    ãĤ§
    -0.66
    mie
    -0.66
    itar
    -0.66
    pace
    -0.65
    bucks
    -0.65
    lins
    -0.65
    izont
    -0.62
    POSITIVE LOGITS
     escort
    1.29
     escorted
    1.23
     esc
    0.96
     attendants
    0.83
    cade
    0.77
    ragon
    0.75
    andowski
    0.72
    ublic
    0.70
     accomp
    0.70
    ĺħ
    0.68
    Activations Density 0.013%

    No Known Activations