© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 16933
    Prev
    Next
    INDEX
    Explanations

    words related to conflict or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "clash" and its variations in different contexts

    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
    enfranch
    -0.81
    mental
    -0.80
    duct
    -0.78
    ufact
    -0.77
    secut
    -0.75
    employment
    -0.72
    requisite
    -0.69
    ¥µ
    -0.69
    incarn
    -0.68
    ©¶æ¥µ
    -0.67
    POSITIVE LOGITS
     clash
    0.98
     clashes
    0.92
    halla
    0.88
     Clash
    0.74
    mosp
    0.73
     between
    0.71
     looms
    0.70
     Amon
    0.69
     pits
    0.68
     Qiao
    0.68
    Activations Density 0.012%

    No Known Activations