© 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. 12-RES-JB
    11. 4645
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical values related to economic trends and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numerical data related to statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     suffice
    -0.54
     Rend
    -0.53
     Tub
    -0.53
     thous
    -0.52
    forth
    -0.49
     Rib
    -0.48
     Alma
    -0.48
     EntityItem
    -0.47
     Mess
    -0.47
     goodbye
    -0.46
    POSITIVE LOGITS
    ½
    1.05
    .
    1.04
    ·
    1.02
     percentage
    1.01
    %.
    0.95
    %,
    0.93
    %)
    0.91
     percent
    0.91
    %),
    0.90
    %
    0.90
    Activations Density 0.164%

    No Known Activations