© 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. 22241
    Prev
    Next
    INDEX
    Explanations

    references to the term "Motor"

    oai_token-act-pair · gpt-3.5-turbo

    references to automobile manufacturers and related terminology

    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
    ylum
    -0.81
    xual
    -0.80
    wered
    -0.77
    yip
    -0.74
    avorite
    -0.69
     Foley
    -0.69
    é¾įåĸļ士
    -0.67
     BET
    -0.66
    inventoryQuantity
    -0.66
    代
    -0.66
    POSITIVE LOGITS
    cycle
    1.42
    cycles
    1.22
    cycl
    0.93
    cars
    0.91
    company
    0.83
    wagen
    0.83
    Spec
    0.81
    immune
    0.79
    puter
    0.79
    Storm
    0.78
    Activations Density 0.009%

    No Known Activations