© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12763
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that describe something as exceptional or standout compared to some standard

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "by" followed by a measurement or standard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idad
    -0.71
    heed
    -0.69
    regon
    -0.65
     fres
    -0.64
    ivia
    -0.63
    bian
    -0.61
    gin
    -0.61
    LO
    -0.61
    wine
    -0.61
    inea
    -0.60
    POSITIVE LOGITS
     virtue
    1.26
    products
    1.03
     implication
    1.00
     default
    0.98
     comparison
    0.92
    product
    0.88
     contrast
    0.87
    laws
    0.87
    akuya
    0.83
     2050
    0.82
    Activations Density 0.121%

    No Known Activations