© 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. 24290
    Prev
    Next
    INDEX
    Explanations

    words related to taking action or carrying out tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote processes or actions that are necessary to achieve a specific goal or outcome

    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
    tu
    -0.72
    tex
    -0.72
    oat
    -0.70
    eworld
    -0.65
    inav
    -0.65
    tty
    -0.64
    der
    -0.63
    raped
    -0.63
    vas
    -0.63
    odd
    -0.63
    POSITIVE LOGITS
     Osw
    0.72
     to
    0.71
     thereto
    0.70
     facilitate
    0.66
    meal
    0.65
     induction
    0.61
     bolster
    0.61
    aration
    0.61
     perpetuate
    0.61
    ":"/
    0.60
    Activations Density 0.035%

    No Known Activations