© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13999
    Prev
    Next
    INDEX
    Explanations

    compound words and phrases with the word "hard-" as a prefix

    oai_token-act-pair · gpt-3.5-turbo

    references to "hard" situations or challenges, particularly in the context of labor and economic issues

    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
     revel
    -0.73
     commencement
    -0.67
     incorpor
    -0.66
     elim
    -0.64
     incorporation
    -0.64
     lux
    -0.63
     Burk
    -0.63
    ;;;;;;;;;;;;
    -0.63
     Wonderland
    -0.62
     Rica
    -0.61
    POSITIVE LOGITS
    hitting
    1.57
    pressed
    1.43
    earned
    1.41
    edged
    1.35
    working
    1.32
    charging
    1.31
    luck
    1.27
    core
    1.27
    driving
    1.26
    coded
    1.25
    Activations Density 0.023%

    No Known Activations