© 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. 8-RES-JB
    11. 14182
    Prev
    Next
    INDEX
    Explanations

    references to flags

    oai_token-act-pair · gpt-3.5-turbo

    mentions of flags

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    女
    -0.78
     Flavoring
    -0.77
     subsequ
    -0.76
    nesota
    -0.72
    axter
    -0.72
     toget
    -0.71
    è£ħ
    -0.69
     Kut
    -0.69
    oice
    -0.68
    izabeth
    -0.66
    POSITIVE LOGITS
    pole
    1.42
    ging
    1.36
    rant
    1.32
    staff
    1.29
     bearer
    1.09
    ged
    1.03
    ribute
    0.91
    Flag
    0.88
    stones
    0.87
    gers
    0.87
    Activations Density 0.032%

    No Known Activations