© 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. 4-RES-JB
    11. 13416
    Prev
    Next
    INDEX
    Explanations

    the word "spokeswoman" in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespersons or spokesperson-related terminology

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

    No Comments

    Negative Logits
    rament
    -0.76
    akespe
    -0.66
    vernment
    -0.65
     insepar
    -0.65
    SPONSORED
    -0.65
    ozy
    -0.63
     thirsty
    -0.62
    ypes
    -0.62
    undo
    -0.62
    usalem
    -0.61
    POSITIVE LOGITS
     Anne
    1.04
     Marie
    0.95
     Louise
    0.94
    Anne
    0.94
     Nicole
    0.93
     Maria
    0.92
     Isabel
    0.87
     Mary
    0.87
     maid
    0.84
    cule
    0.83
    Activations Density 0.029%

    No Known Activations