© 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. 9-RES-JB
    11. 10172
    Prev
    Next
    INDEX
    Explanations

    the word "catch" used in various contexts or expressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of a "catch" or paradoxical situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sclerosis
    -0.78
    urred
    -0.73
     princip
    -0.68
    opausal
    -0.64
    eled
    -0.64
     splash
    -0.64
     dominant
    -0.62
    PDATE
    -0.62
    uilt
    -0.61
    ovych
    -0.61
    POSITIVE LOGITS
    phrase
    1.39
    bowl
    0.88
    apon
    0.86
    backs
    0.86
    aways
    0.86
    trap
    0.85
    amac
    0.83
    pole
    0.82
    athon
    0.80
    iest
    0.77
    Activations Density 0.033%

    No Known Activations