© 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 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. 24270
    Prev
    Next
    INDEX
    Explanations

    verbs related to commanding or strongly stating a position

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "insist" and its variations

    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
    gone
    -0.80
    brance
    -0.72
    posure
    -0.70
    ggies
    -0.64
    ________________
    -0.62
    izons
    -0.61
    fecture
    -0.61
    Kin
    -0.61
     NCT
    -0.60
     Radiation
    -0.60
    POSITIVE LOGITS
    ially
    0.83
    ently
    0.79
    onite
    0.76
    encies
    0.75
    uca
    0.75
    iago
    0.74
     vehemently
    0.73
    chev
    0.73
    oux
    0.72
     insist
    0.72
    Activations Density 0.017%

    No Known Activations