© 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. 1-RES-JB
    11. 2506
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Brady" and its variations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.84
     AMERICA
    -0.78
    eers
    -0.73
    sold
    -0.69
    66666666
    -0.66
     Modest
    -0.63
     CONTROL
    -0.63
     Monarch
    -0.63
    rers
    -0.62
     Falling
    -0.62
    POSITIVE LOGITS
    acket
    1.18
    ackets
    1.04
    unn
    0.98
    atcher
    0.98
    atton
    0.96
    itt
    0.92
    Br
    0.89
    asso
    0.88
    itton
    0.88
    ients
    0.86
    Activations Density 0.006%

    No Known Activations