© 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. 1-RES-JB
    11. 11405
    Prev
    Next
    INDEX
    Explanations

    terms related to trucks and vehicles

    oai_token-act-pair · gpt-3.5-turbo

    references to trucks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Liberties
    -0.85
    ASED
    -0.77
    ANC
    -0.73
    AE
    -0.70
    âĸ¬âĸ¬
    -0.70
     Nation
    -0.69
    mary
    -0.69
    ENC
    -0.68
    âĸ¬
    -0.68
    ERAL
    -0.68
    POSITIVE LOGITS
     trucks
    1.46
     truck
    1.13
     vans
    0.99
    wagon
    0.98
    loads
    0.90
     cars
    0.90
     tractor
    0.87
     taxis
    0.87
     motorcycles
    0.86
     parked
    0.82
    Activations Density 0.010%

    No Known Activations