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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2783
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effectiveness or impact of actions or interventions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the effectiveness or impact of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibrary
    -0.65
    ynski
    -0.64
    skip
    -0.59
    oston
    -0.59
    ricting
    -0.58
     Drops
    -0.57
    roid
    -0.56
     boards
    -0.54
     hindsight
    -0.54
     Venture
    -0.54
    POSITIVE LOGITS
     wonders
    1.04
     harm
    0.97
     justice
    0.85
     damage
    0.83
     lasting
    0.79
     trick
    0.79
     untold
    0.78
     miracles
    0.77
     favors
    0.74
    duty
    0.73
    Activations Density 0.130%

    No Known Activations