© 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. 10115
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    negative prefixes and suffixes in words or phrases

    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
     Jackets
    -0.88
     Torrent
    -0.78
     circle
    -0.75
     Noise
    -0.72
     Survivors
    -0.72
     Velocity
    -0.72
     Venice
    -0.71
     WTC
    -0.70
     ado
    -0.69
     LOT
    -0.68
    POSITIVE LOGITS
    defined
    1.28
    developed
    1.25
    connected
    1.23
    produced
    1.23
    generated
    1.22
    trained
    1.22
    assembled
    1.20
    designed
    1.20
    accessible
    1.19
    placed
    1.17
    Activations Density 0.057%

    No Known Activations