© 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. 6055
    Prev
    Next
    INDEX
    Explanations

    dates in the format "April X"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific dates, particularly in April

    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
    ancial
    -0.74
    opic
    -0.62
    XT
    -0.60
    desc
    -0.60
    ted
    -0.59
     phyl
    -0.59
    ategory
    -0.58
     neigh
    -0.54
     maxim
    -0.54
    enes
    -0.54
    POSITIVE LOGITS
     Fool
    1.45
     29
    0.93
    eteenth
    0.92
     28
    0.91
    fair
    0.90
     27
    0.90
     26
    0.89
     Madness
    0.87
     fools
    0.86
    flower
    0.85
    Activations Density 0.048%

    No Known Activations