© 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. 11-RES-JB
    11. 6494
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicles, particularly manual transmission and control functions

    oai_token-act-pair · gpt-3.5-turbo

    automotive technical specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coffin
    -0.80
     plagiar
    -0.76
     Nether
    -0.76
    代
    -0.75
     Stain
    -0.73
     Hallow
    -0.71
     Flan
    -0.69
    azo
    -0.69
     Melania
    -0.69
     Patreon
    -0.69
    POSITIVE LOGITS
     steering
    1.47
     braking
    1.46
     brake
    1.39
     brakes
    1.34
     joystick
    1.31
     throttle
    1.30
     pedals
    1.29
     controls
    1.25
     ignition
    1.24
     wip
    1.23
    Activations Density 0.323%

    No Known Activations