© 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 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. 3-RES-JB
    11. 24205
    Prev
    Next
    INDEX
    Explanations

    references to the year 1930 or 1932

    oai_token-act-pair · gpt-3.5-turbo

    references to the 1930s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledged
    -0.80
    holder
    -0.75
    atives
    -0.73
    Kin
    -0.72
    ates
    -0.70
    orable
    -0.68
    player
    -0.66
    iant
    -0.66
    isters
    -0.66
    ema
    -0.66
    POSITIVE LOGITS
     1936
    0.86
     1934
    0.82
    é¾įå¥ij士
    0.79
     1938
    0.78
     1935
    0.76
    éĹĺ
    0.74
    é¾įåĸļ士
    0.74
     1937
    0.74
     Reincarn
    0.74
     1933
    0.73
    Activations Density 0.013%

    No Known Activations