© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    scientific terms and technical jargon related to physics and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant scientific discoveries and political issues

    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
    itars
    -0.92
    ials
    -0.84
    igne
    -0.78
    requ
    -0.78
    govtrack
    -0.77
    rower
    -0.77
    umar
    -0.76
    arily
    -0.75
    arf
    -0.74
    ocal
    -0.71
    POSITIVE LOGITS
     Initiative
    0.88
     Amendments
    0.81
    Ħ¢
    0.81
     Project
    0.76
     Era
    0.75
     Secure
    0.72
     Foundation
    0.70
     Amendment
    0.70
    Gate
    0.69
    Secure
    0.69
    Activations Density 0.249%

    No Known Activations