© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 19564
    Prev
    Next
    INDEX
    Explanations

    mentions of autonomous technology and vehicles

    oai_token-act-pair · gpt-3.5-turbo

    references to autonomous technology or vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Garn
    -0.71
     Cron
    -0.71
    lyn
    -0.70
     brim
    -0.69
    rette
    -0.69
    nut
    -0.68
    cloth
    -0.68
     Angelo
    -0.66
    COL
    -0.66
     Stamp
    -0.66
    POSITIVE LOGITS
     autonomous
    3.67
    onomous
    2.40
     autonomy
    2.27
     autonom
    1.96
     Aut
    1.51
     unmanned
    1.50
     automated
    1.19
     autop
    1.18
     independence
    1.18
     decentralized
    1.16
    Activations Density 0.019%

    No Known Activations