© 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. 2-RES-JB
    11. 13826
    Prev
    Next
    INDEX
    Explanations

    numbers representing ages

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical statistics or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.90
    uyomi
    -0.74
    urus
    -0.72
    folk
    -0.70
    parency
    -0.66
    furt
    -0.64
    è¯
    -0.62
    lied
    -0.61
    ramid
    -0.59
    hist
    -0.58
    POSITIVE LOGITS
    %"
    0.97
    %-
    0.94
    %,
    0.93
     cents
    0.93
    %
    0.92
    ¢
    0.91
    %:
    0.90
     percent
    0.85
    %.
    0.79
     stitches
    0.77
    Activations Density 0.082%

    No Known Activations