© 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. 11292
    Prev
    Next
    INDEX
    Explanations

    statistics or data related terms including 'Stats' and 'Map'

    oai_token-act-pair · gpt-3.5-turbo

    sections related to statistical data and performance metrics

    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
     toler
    -0.73
     wheel
    -0.70
     oxide
    -0.70
     fre
    -0.70
     overboard
    -0.70
    enf
    -0.70
     wake
    -0.69
     mess
    -0.68
     prototyp
    -0.68
     ecstasy
    -0.68
    POSITIVE LOGITS
     Stats
    3.61
    Stats
    1.76
     Map
    1.31
     STATS
    1.20
     Info
    1.18
     Statistics
    1.11
     Stat
    1.09
    stats
    1.08
     Tracker
    1.08
    Statistics
    1.06
    Activations Density 0.031%

    No Known Activations