© 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. 10264
    Prev
    Next
    INDEX
    Explanations

    sentences that end in a period surrounded by whitespace

    oai_token-act-pair · gpt-3.5-turbo

    endings of sentences or periods in a narrative context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    velop
    -0.83
    reet
    -0.74
     bench
    -0.73
    hesda
    -0.71
     ballistic
    -0.71
    tera
    -0.71
     pros
    -0.69
     carpet
    -0.68
     spons
    -0.68
    zik
    -0.68
    POSITIVE LOGITS
     Written
    1.58
     Meanwhile
    1.45
     Along
    1.26
     Eventually
    1.22
     Luckily
    1.19
     Throughout
    1.17
     Forced
    1.17
     Though
    1.17
     Fortunately
    1.16
     Together
    1.15
    Activations Density 0.213%

    No Known Activations