© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10377
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or phrases where an entity or object is introduced

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Own
    -0.75
    anism
    -0.73
    bas
    -0.70
    apest
    -0.68
    antry
    -0.68
    Arcade
    -0.68
    AIDS
    -0.67
    agree
    -0.67
    via
    -0.67
    <?
    -0.67
    POSITIVE LOGITS
     handful
    1.03
     colleague
    1.02
     couple
    0.99
     woman
    0.98
     reader
    0.95
     flurry
    0.94
     staffer
    0.94
     policeman
    0.93
     member
    0.92
     technician
    0.92
    Activations Density 0.213%

    No Known Activations