© 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. 20884
    Prev
    Next
    INDEX
    Explanations

    phrases related to going somewhere or returning from somewhere

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate possession or a relationship to something

    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
    insula
    -0.79
    blade
    -0.73
    ividual
    -0.67
    orp
    -0.65
     Specifically
    -0.64
    ever
    -0.62
    ecycle
    -0.62
    hower
    -0.61
    etts
    -0.61
    chan
    -0.60
    POSITIVE LOGITS
    stood
    1.15
     impunity
    1.10
    draw
    1.05
     dignity
    1.03
     regrets
    1.03
    drawn
    1.01
     hopes
    0.92
     caveats
    0.92
     regards
    0.87
     renewed
    0.87
    Activations Density 0.145%

    No Known Activations