© 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. 14256
    Prev
    Next
    INDEX
    Explanations

    words related to car parts, specifically the term "bumper."

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicle bumpers

    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
    ulu
    -0.79
    omen
    -0.74
    aves
    -0.73
    arin
    -0.69
    aldo
    -0.68
    DEN
    -0.67
    uld
    -0.67
    udes
    -0.67
    oyer
    -0.66
    ollywood
    -0.65
    POSITIVE LOGITS
     bumper
    1.35
     sticker
    1.04
     stickers
    1.03
     crates
    0.83
     wip
    0.81
     billboards
    0.78
    stick
    0.76
    cars
    0.74
     crate
    0.74
    sticks
    0.73
    Activations Density 0.008%

    No Known Activations