© 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. 12201
    Prev
    Next
    INDEX
    Explanations

    phrases related to discipline or criticism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criticism and reprimanding behaviors

    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
     misunder
    -0.65
    ipeg
    -0.64
    change
    -0.63
     incub
    -0.63
    Mos
    -0.61
     stock
    -0.61
    markets
    -0.60
     resid
    -0.60
     autonomous
    -0.60
     embryo
    -0.60
    POSITIVE LOGITS
    imaru
    0.86
    erous
    0.82
     rebuke
    0.79
     politely
    0.76
    isance
    0.72
     reprim
    0.71
    severe
    0.71
     admon
    0.71
    >>\
    0.71
    Rated
    0.69
    Activations Density 0.058%

    No Known Activations