© 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. 5109
    Prev
    Next
    INDEX
    Explanations

    statements related to political or legal controversies

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

    sentences that end with a period

    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
     tremend
    -1.45
     satell
    -1.41
     challeng
    -1.39
     millenn
    -1.25
     gobl
    -1.24
     volunte
    -1.15
     subsequ
    -1.13
    undai
    -1.13
    ¥ŀ
    -1.12
     unnecess
    -1.05
    POSITIVE LOGITS
     Asked
    1.52
     Speaking
    1.47
     "[
    1.40
     Saying
    1.33
     "'
    1.30
     He
    1.29
     "
    1.27
     Specifically
    1.25
     "(
    1.25
     Regarding
    1.25
    Activations Density 0.409%

    No Known Activations