© 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. 10220
    Prev
    Next
    INDEX
    Explanations

    sentences indicating customer service responses or communications

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods and commas

    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
    ŃĶ
    -0.95
    zee
    -0.71
    ãĥ©ãĥ³
    -0.66
    alions
    -0.66
     indistinguishable
    -0.65
    oho
    -0.65
    eteen
    -0.65
     affili
    -0.64
    iphate
    -0.63
     admire
    -0.63
    POSITIVE LOGITS
     Fortunately
    1.92
     Luckily
    1.89
     Consequently
    1.82
     Therefore
    1.81
     Worse
    1.81
     Thankfully
    1.78
     Nevertheless
    1.70
     Nonetheless
    1.67
     Hence
    1.58
    Fortunately
    1.55
    Activations Density 0.546%

    No Known Activations