© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8768
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to famous individuals like "Irana," "meilda," and "Silverman" that are not necessarily linked by shared characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    patterns of repeated syllables or phonetic sounds in the text

    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
     Redemption
    -0.58
     RU
    -0.57
     reload
    -0.55
     Reyes
    -0.55
     NIGHT
    -0.55
     wig
    -0.54
     fingerprints
    -0.54
     bur
    -0.54
     Cherokee
    -0.54
     bailed
    -0.53
    POSITIVE LOGITS
    acan
    1.09
    é¾įå
    0.87
    olit
    0.86
    throp
    0.78
    orio
    0.77
    annis
    0.75
    heart
    0.73
    ACA
    0.72
    archs
    0.72
    umerable
    0.71
    Activations Density 0.077%

    No Known Activations