© 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. 9-RES-JB
    11. 10375
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or advocating for change

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Got
    -0.61
    lights
    -0.60
    âĿ
    -0.59
    pie
    -0.59
    aneous
    -0.59
    Mur
    -0.59
    rider
    -0.57
     versus
    -0.57
    *
    -0.57
    UR
    -0.56
    POSITIVE LOGITS
     minimize
    1.06
     insure
    1.05
     intensify
    1.05
     educate
    1.04
     demonstrate
    1.04
     facilitate
    1.02
     relieve
    1.01
     undertake
    1.01
     avoid
    1.01
     degrade
    1.01
    Activations Density 0.138%

    No Known Activations