© 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. 7539
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of something being ridiculous

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ridiculous."

    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
    enegger
    -0.79
    avorite
    -0.75
    HAEL
    -0.65
    arser
    -0.65
     largeDownload
    -0.62
     sustaining
    -0.60
     flap
    -0.59
     Markets
    -0.58
    EEK
    -0.58
     Remem
    -0.57
    POSITIVE LOGITS
    gements
    1.13
    gew
    1.11
    ged
    1.10
    gement
    1.07
    gments
    1.07
    uces
    1.05
    gment
    1.05
    uction
    1.01
    ging
    1.00
    der
    0.97
    Activations Density 0.010%

    No Known Activations