© 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. 8-RES-JB
    11. 3168
    Prev
    Next
    INDEX
    Explanations

    titles of video games or movies

    oai_token-act-pair · gpt-3.5-turbo

    colons followed by movie or TV show titles

    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
     tremend
    -0.85
    uggest
    -0.82
    jri
    -0.77
     trouble
    -0.77
    etooth
    -0.76
    yout
    -0.73
    inarily
    -0.72
     commentator
    -0.71
     benches
    -0.70
     advertis
    -0.67
    POSITIVE LOGITS
     Reborn
    0.97
     Resurrection
    0.92
     Andromeda
    0.92
     Ascension
    0.92
     Become
    0.92
     Rebirth
    0.91
    Battle
    0.91
     Rise
    0.90
     Legendary
    0.89
     Portable
    0.89
    Activations Density 0.054%

    No Known Activations