© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making, strategic directions or plans

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

    instances of the word "go" in various forms and contexts

    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
    rika
    -0.86
    ariat
    -0.76
    ullah
    -0.70
    $$$$
    -0.68
    tumblr
    -0.67
    itude
    -0.62
    eers
    -0.61
    eve
    -0.61
    Gov
    -0.61
    tta
    -0.61
    POSITIVE LOGITS
     overboard
    1.09
     ahead
    0.85
     minimalist
    0.73
     rogue
    0.72
     bold
    0.71
     DIY
    0.71
     Commando
    0.71
     nuts
    0.69
    aded
    0.68
     HAM
    0.68
    Activations Density 0.070%

    No Known Activations