© 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. 11380
    Prev
    Next
    INDEX
    Explanations

    contrasting relationships or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    contrasting phrases that highlight alternative perspectives or nuances in discussions

    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
    fuck
    -0.67
    elta
    -0.62
    cig
    -0.61
    hent
    -0.61
    ~~~~
    -0.59
    ~~~~~~~~
    -0.59
     Then
    -0.58
    iframe
    -0.56
    socket
    -0.55
    rollers
    -0.55
    POSITIVE LOGITS
     whether
    1.10
     how
    1.01
     regarding
    0.92
    cific
    0.87
     insofar
    0.84
     concerns
    0.83
     concerning
    0.82
    whether
    0.81
     perceptions
    0.81
     assessing
    0.79
    Activations Density 0.257%

    No Known Activations