© 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. 10616
    Prev
    Next
    INDEX
    Explanations

    adjectives describing beauty or excellence

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and adjectives that convey beauty or excellence

    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
    gate
    -0.75
    eport
    -0.72
     administration
    -0.71
    gments
    -0.71
     restraints
    -0.69
    hao
    -0.67
     inaction
    -0.66
     LCS
    -0.65
     newsp
    -0.65
     gateway
    -0.64
    POSITIVE LOGITS
     suited
    0.87
    baum
    0.85
     illustrated
    0.84
     Designed
    0.77
    ãĤ¼ãĤ¦ãĤ¹
    0.73
    BuyableInstoreAndOnline
    0.71
     impressed
    0.71
     adapted
    0.71
     tuned
    0.70
    istered
    0.70
    Activations Density 0.034%

    No Known Activations