© 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. 12-RES-JB
    11. 5102
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or events, specifically focusing on the recurring mention of "Red."

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to the color red and its associated entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     uncom
    -0.59
     behold
    -0.57
    SPONSORED
    -0.55
     animate
    -0.55
     incorpor
    -0.54
     creation
    -0.54
     IM
    -0.53
     suffice
    -0.53
     yes
    -0.52
     err
    -0.52
    POSITIVE LOGITS
    eem
    1.18
    emption
    1.18
    ucing
    1.16
    acted
    1.06
    ucer
    1.06
    irect
    1.04
    ondo
    1.03
    ding
    1.02
    iscover
    1.02
     Sox
    1.01
    Activations Density 0.027%

    No Known Activations