© 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. 4-RES-JB
    11. 7366
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of vehicles such as scooters, trolleys, and rollers

    oai_token-act-pair · gpt-3.5-turbo

    references to scooters and similar wheeled vehicles

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

    No Comments

    Negative Logits
    £ı
    -0.66
    ĨĴ
    -0.66
     unsolved
    -0.65
    nant
    -0.64
     cryst
    -0.64
     acknowled
    -0.63
     flesh
    -0.63
    quartered
    -0.62
     mysterious
    -0.61
     newsp
    -0.61
    POSITIVE LOGITS
    ooter
    0.99
    inson
    0.94
    oad
    0.90
    Cop
    0.83
    ooters
    0.80
    swick
    0.79
    cade
    0.79
    glers
    0.78
    hoe
    0.76
    zes
    0.75
    Activations Density 0.029%

    No Known Activations