© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5113
    Prev
    Next
    INDEX
    Explanations

    technical details related to car parts and performance

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    high-performance vehicle specifications and features

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    arantine
    -0.78
    tsy
    -0.78
    aman
    -0.74
    pora
    -0.74
    hemat
    -0.73
    uin
    -0.72
    umbnail
    -0.72
     Username
    -0.72
    umbn
    -0.72
    xus
    -0.69
    POSITIVE LOGITS
     braking
    1.48
     acceleration
    1.39
     torque
    1.34
     throttle
    1.30
     traction
    1.26
     brakes
    1.23
     horsepower
    1.19
     cruise
    1.17
     brake
    1.16
     cruising
    1.15
    Activations Density 0.289%

    No Known Activations