© 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. 10-RES-JB
    11. 12079
    Prev
    Next
    INDEX
    Explanations

    photo captions with locations or references to photography-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iously
    -0.61
     controvers
    -0.61
    iband
    -0.60
     patches
    -0.60
     tit
    -0.59
    !).
    -0.59
    GP
    -0.59
     stakes
    -0.58
    agonist
    -0.58
     mobs
    -0.56
    POSITIVE LOGITS
    window
    1.29
     Buy
    0.98
    taboola
    0.94
     FILE
    0.90
     Image
    0.88
     File
    0.87
     Chronicle
    0.86
    FILE
    0.84
     Photo
    0.81
     less
    0.80
    Activations Density 0.047%

    No Known Activations