© 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. 4-RES-JB
    11. 895
    Prev
    Next
    INDEX
    Explanations

    metaphorical and figurative language related to complexity, challenges, and potential dangers

    oai_token-act-pair · gpt-3.5-turbo

    metaphorical phrases that convey a sense of challenge or complexity

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

    No Comments

    Negative Logits
     Lod
    -0.76
     Instr
    -0.68
     Expression
    -0.68
    ¿
    -0.67
    itu
    -0.67
    ials
    -0.62
     Planes
    -0.62
     Farn
    -0.62
    rams
    -0.61
    arel
    -0.61
    POSITIVE LOGITS
     iceberg
    0.76
     ¯
    0.72
     paradise
    0.71
     maze
    0.70
     tails
    0.70
     extraord
    0.66
    ãĤ´ãĥ³
    0.65
     fallacy
    0.65
     loser
    0.64
     bargain
    0.64
    Activations Density 0.220%

    No Known Activations