© 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. 3-RES-JB
    11. 17217
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or concept named "Aggie"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group or entity referred to as "Aggies"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãĤ´ãĥ³
    -0.91
    姫
    -0.84
    代
    -0.78
    phrine
    -0.74
    çīĪ
    -0.73
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
    çĦ
    -0.70
     Nadu
    -0.66
    UTION
    -0.65
    VEL
    -0.64
    POSITIVE LOGITS
    regate
    1.43
    ressive
    1.23
    Agg
    1.14
    raph
    1.04
    ression
    1.03
    regation
    1.03
    ressor
    1.00
    irlf
    0.95
    eties
    0.93
    regor
    0.91
    Activations Density 0.008%

    No Known Activations