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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9457
    Prev
    Next
    INDEX
    Explanations

    phrases describing capability, often related to technological or physical abilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capabilities or potential of entities

    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
    ritz
    -0.71
    bilt
    -0.69
    imize
    -0.69
    lass
    -0.67
    rones
    -0.61
    redit
    -0.61
    fty
    -0.61
    zag
    -0.61
    wind
    -0.60
    owan
    -0.60
    POSITIVE LOGITS
     producing
    1.41
     delivering
    1.40
     sustaining
    1.37
     achieving
    1.33
     inflicting
    1.32
     extracting
    1.32
     distinguishing
    1.31
     completing
    1.28
     providing
    1.28
     capturing
    1.27
    Activations Density 0.070%

    No Known Activations