© 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. 10207
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress and advancement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "move forward"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    chens
    -0.64
    BuyableInstoreAndOnline
    -0.63
    gments
    -0.63
    azo
    -0.62
    jah
    -0.60
     downed
    -0.60
    ãĤ¦ãĤ¹
    -0.60
     Rove
    -0.60
    hee
    -0.59
    ENA
    -0.59
    POSITIVE LOGITS
     unnoticed
    0.81
     academ
    0.81
     unim
    0.81
     toward
    0.80
    WARD
    0.80
    olicy
    0.79
     with
    0.78
     unch
    0.78
     towards
    0.78
    stage
    0.73
    Activations Density 0.039%

    No Known Activations