© 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. 20756
    Prev
    Next
    INDEX
    Explanations

    words related to competence and incompetence

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with competence and incompetence in various contexts

    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
    forest
    -0.77
    den
    -0.75
    eed
    -0.74
    hop
    -0.73
    Pause
    -0.72
    eda
    -0.70
    patch
    -0.70
    eper
    -0.70
    Hop
    -0.70
    fter
    -0.69
    POSITIVE LOGITS
     incompetent
    1.10
    glers
    1.06
     competent
    1.04
     incompetence
    0.93
    umbn
    0.89
     incompet
    0.87
     competence
    0.86
    abama
    0.84
    inois
    0.81
    ocrats
    0.76
    Activations Density 0.029%

    No Known Activations