© 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. 0-RES-JB
    11. 5227
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer applications, specifically apps and software systems like Unity Launcher

    oai_token-act-pair · gpt-3.5-turbo

    references to digital applications and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     symbol
    -0.70
     pinch
    -0.66
     relative
    -0.66
     arrow
    -0.66
     Song
    -0.65
     Mane
    -0.64
     Prayer
    -0.62
    ulus
    -0.62
     procedure
    -0.60
    Materials
    -0.59
    POSITIVE LOGITS
    asters
    2.69
    apps
    2.63
    boards
    1.77
    Apps
    1.67
    idges
    0.96
    brow
    0.87
    users
    0.82
    AME
    0.80
    plays
    0.79
    adden
    0.79
    Activations Density 0.045%

    No Known Activations