© 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. 2-RES-JB
    11. 12025
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone being guided or accompanied by others in various situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "escorted" and its variations, indicating the act of guiding or leading someone from one place to another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulz
    -0.87
    mie
    -0.75
    ttp
    -0.68
    Month
    -0.66
    lik
    -0.64
    midt
    -0.64
    EMS
    -0.64
    itar
    -0.62
    bucks
    -0.62
    licks
    -0.62
    POSITIVE LOGITS
     escort
    1.19
     escorted
    1.13
     esc
    0.91
    cade
    0.82
     deleg
    0.76
    entimes
    0.71
    ragon
    0.70
     attendants
    0.70
    areth
    0.70
    ographed
    0.69
    Activations Density 0.009%

    No Known Activations