© 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. 21042
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a typical or expected outcome or behavior

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate common characteristics or typical behaviors

    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
     possibly
    -0.72
    amins
    -0.66
    hab
    -0.65
    ingly
    -0.65
    together
    -0.64
    iage
    -0.62
    DNA
    -0.62
    ————————
    -0.61
    yle
    -0.61
     potentially
    -0.60
    POSITIVE LOGITS
     reserved
    0.94
     speaking
    0.81
     refers
    0.75
     wont
    0.75
     suspects
    0.74
     associated
    0.73
     disclaim
    0.71
     consists
    0.71
     accompanies
    0.69
     regarded
    0.69
    Activations Density 0.106%

    No Known Activations