© 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. 9457
    Prev
    Next
    INDEX
    Explanations

    words related to legal and political matters

    oai_token-act-pair · gpt-3.5-turbo

    a specific symbol or character in the text, suggesting it looks for the presence of special characters or symbols

    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
     clitor
    -0.82
     targeted
    -0.74
     spir
    -0.72
     pigeon
    -0.71
     indo
    -0.71
     bounty
    -0.70
     couch
    -0.70
     reflex
    -0.69
     appropri
    -0.69
     barg
    -0.69
    POSITIVE LOGITS
    ï¸ı
    1.40
    ï¸
    1.02
    ternity
    0.96
    Reason
    0.88
    \/\/
    0.87
    uthor
    0.86
    Previously
    0.86
    Discuss
    0.84
    Wr
    0.84
    Roberts
    0.84
    Activations Density 0.156%

    No Known Activations