© 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. 11094
    Prev
    Next
    INDEX
    Explanations

    words related to sleek and glossy appearances

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe smoothness or high quality

    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
    ENTS
    -0.76
    ANN
    -0.76
    ARM
    -0.73
    mare
    -0.68
    foreseen
    -0.67
     Veter
    -0.67
    thur
    -0.66
    ¬¼
    -0.65
    ommod
    -0.65
    phant
    -0.63
    POSITIVE LOGITS
     slick
    1.09
    ness
    0.92
    heet
    0.89
    idious
    0.82
    glers
    0.78
    yne
    0.77
    ened
    0.73
    iness
    0.72
    ening
    0.69
     glossy
    0.69
    Activations Density 0.025%

    No Known Activations