© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4253
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and identifiers in structured data or logs

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     tallied
    -0.63
     waivers
    -0.60
    jri
    -0.60
     fortnight
    -0.59
     reconc
    -0.59
     briefs
    -0.59
     Ging
    -0.56
    ulet
    -0.56
     transcription
    -0.55
     Beir
    -0.55
    POSITIVE LOGITS
    :{
    0.83
    Interstitial
    0.78
    ACTED
    0.77
    Ïī
    0.74
    =>
    0.73
    NetMessage
    0.71
     istg
    0.68
    Ü
    0.68
    lam
    0.67
    Height
    0.67
    Activations Density 0.081%

    No Known Activations