© 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. 6-RES-JB
    11. 9412
    Prev
    Next
    INDEX
    Explanations

    vehicles brands and models

    oai_token-act-pair · gpt-3.5-turbo

    specific vehicle and transportation-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hallow
    -0.74
    Filename
    -0.69
     Sabb
    -0.67
    pmwiki
    -0.67
     Relations
    -0.65
     Restaur
    -0.64
     organised
    -0.64
    iferation
    -0.63
     precincts
    -0.63
    relations
    -0.63
    POSITIVE LOGITS
     chassis
    1.04
     Turbo
    0.94
     equipped
    0.91
    equipped
    0.90
     RX
    0.90
     handheld
    0.86
     tilt
    0.86
    wagen
    0.84
     Mk
    0.83
     convertible
    0.83
    Activations Density 0.875%

    No Known Activations