© 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 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. 3-RES-JB
    11. 5537
    Prev
    Next
    INDEX
    Explanations

    terminology related to conflicts or contradictions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "con" in various forms, likely indicating concepts related to conflict or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAEL
    -0.73
    chens
    -0.71
     Bye
    -0.64
     Giov
    -0.63
    assetsadobe
    -0.63
     Rover
    -0.62
     GOODMAN
    -0.62
     Forth
    -0.62
     Bulg
    -0.60
     Pry
    -0.60
    POSITIVE LOGITS
    structed
    1.16
    venient
    1.15
    ventions
    1.09
    secut
    1.06
    vention
    1.04
    currency
    1.03
    crete
    1.00
    naissance
    0.99
    ceived
    0.98
    ventional
    0.96
    Activations Density 0.006%

    No Known Activations