© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 7097
    Prev
    Next
    INDEX
    Explanations

    references to items being transported or carried as cargo

    oai_token-act-pair · gpt-3.5-turbo

    references to cargo or shipments in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nich
    -0.84
     Peaks
    -0.78
    owitz
    -0.72
    nces
    -0.69
     Simpson
    -0.68
    lis
    -0.68
     Hyde
    -0.68
    Div
    -0.65
     Bernstein
    -0.65
     NEC
    -0.64
    POSITIVE LOGITS
     cargo
    3.84
     Cargo
    2.92
     luggage
    1.80
     freight
    1.76
     payload
    1.67
    argo
    1.63
     passenger
    1.57
     passengers
    1.54
     crates
    1.52
     baggage
    1.47
    Activations Density 0.016%

    No Known Activations