© 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. 3-RES-JB
    11. 21149
    Prev
    Next
    INDEX
    Explanations

    words related to incompetence or ineptitude

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incompetence and ineptness

    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
    forest
    -0.72
    den
    -0.71
    Origin
    -0.70
    eper
    -0.69
    erness
    -0.68
    leans
    -0.67
    Soul
    -0.65
     unexpl
    -0.65
    alde
    -0.64
    ells
    -0.64
    POSITIVE LOGITS
     incompetent
    1.11
     incompetence
    0.99
    glers
    0.93
     competent
    0.89
     incompet
    0.88
    uracy
    0.80
    ocracy
    0.79
     idiots
    0.79
     inept
    0.76
     excuse
    0.76
    Activations Density 0.024%

    No Known Activations