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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 21842
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "escorting", especially in a legal or protective context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "esc" and its variations indicating escape or escort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dynamics
    -0.83
     isEnabled
    -0.75
    κ
    -0.72
    KER
    -0.72
    WARE
    -0.72
    å§«
    -0.70
    gaard
    -0.68
    REDACTED
    -0.68
    EEE
    -0.66
     Trident
    -0.65
    POSITIVE LOGITS
     esc
    1.16
    ript
    1.15
    ribed
    1.15
    apist
    1.03
    ription
    1.03
    orts
    0.97
    orting
    0.96
    cade
    0.95
    ilit
    0.94
    aped
    0.89
    Activations Density 0.004%

    No Known Activations