© 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. 7-RES-JB
    11. 23886
    Prev
    Next
    INDEX
    Explanations

    phrases related to being caught or caught in a negative situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "caught" related to various contexts of being caught in actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psey
    -0.69
     estimation
    -0.67
    enture
    -0.67
     pronoun
    -0.65
     sclerosis
    -0.65
    uum
    -0.65
    aceutical
    -0.63
    meric
    -0.62
    ankind
    -0.62
    enic
    -0.62
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.81
     unprepared
    0.72
     caught
    0.72
    phrase
    0.72
    netflix
    0.70
    ãĤµ
    0.70
    trap
    0.69
    bryce
    0.69
     Luffy
    0.68
    aught
    0.67
    Activations Density 0.020%

    No Known Activations