© 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. 11-RES-JB
    11. 7525
    Prev
    Next
    INDEX
    Explanations

    descriptive words or phrases that captivate or interest the reader

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "captivate" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DEN
    -0.61
     deaf
    -0.61
     ASD
    -0.59
     Tend
    -0.59
     safety
    -0.57
    lly
    -0.56
     regulations
    -0.55
     bureaucracy
    -0.54
     environmental
    -0.54
     compare
    -0.54
    POSITIVE LOGITS
    ivating
    1.63
    ivated
    1.44
    ured
    1.38
    urable
    1.35
    ains
    1.32
    ions
    1.30
    aining
    1.21
    uring
    1.20
    ivation
    1.19
    ained
    1.18
    Activations Density 0.029%

    No Known Activations