© 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. 7-RES-JB
    6. 11293
    Prev
    Next
    INDEX
    Explanations

    phrases displayed on objects or clothing

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements displayed on clothing or signs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.75
     jails
    -0.72
    bring
    -0.72
    imester
    -0.72
    anship
    -0.70
    flows
    -0.70
    ucket
    -0.69
    enne
    -0.69
    deep
    -0.68
    produ
    -0.68
    POSITIVE LOGITS
     swast
    1.19
     inscription
    1.12
     logos
    1.11
     logo
    1.10
     inscribed
    1.05
     emblem
    0.99
     engraved
    0.95
     etched
    0.95
     insign
    0.95
     slogans
    0.93
    Activations Density 0.521%

    No Known Activations