© 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. 23698
    Prev
    Next
    INDEX
    Explanations

    captions associated with images

    oai_token-act-pair · gpt-3.5-turbo

    references to photos and visuals

    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
    rane
    -0.86
    ministic
    -0.73
    stood
    -0.71
    merce
    -0.69
    rance
    -0.67
    cffff
    -0.65
    lag
    -0.64
    phas
    -0.61
    uster
    -0.60
    antle
    -0.59
    POSITIVE LOGITS
     Photos
    0.77
    س
    0.66
    Gallery
    0.62
    ynthesis
    0.62
    iah
    0.61
     Caption
    0.59
     Angels
    0.58
    å°Ĩ
    0.57
     Vehicles
    0.57
     perks
    0.56
    Activations Density 0.022%

    No Known Activations