© 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. 9-RES-JB
    11. 23205
    Prev
    Next
    INDEX
    Explanations

    instances of words related to conflict or controversy

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to conflict and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.73
    ables
    -0.70
    vale
    -0.70
    aceous
    -0.68
    raltar
    -0.67
    erred
    -0.66
    iates
    -0.66
    ensions
    -0.66
    poor
    -0.63
    imm
    -0.63
    POSITIVE LOGITS
     mentality
    1.12
     waged
    0.91
     perpetrated
    0.89
     hysteria
    0.88
     frenzy
    0.84
     ensued
    0.83
     engulf
    0.81
     wherein
    0.80
     hypothesis
    0.79
     whereby
    0.78
    Activations Density 0.266%

    No Known Activations