© 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. 1-RES-JB
    11. 20506
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to characters or places

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity named "Ar."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    iculty
    -0.79
    stakes
    -0.67
    姫
    -0.67
    ãģ®éŃĶ
    -0.67
    INESS
    -0.65
     Regulatory
    -0.64
     Territories
    -0.64
     Pioneer
    -0.63
    eners
    -0.62
    ¬¼
    -0.61
    POSITIVE LOGITS
    issa
    1.00
    ithmetic
    0.98
    thritis
    0.96
    idon
    0.95
    ranging
    0.90
    atars
    0.90
    izoph
    0.88
    reon
    0.87
    leigh
    0.87
    ranged
    0.85
    Activations Density 0.008%

    No Known Activations