© 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. 10105
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection or defense

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating overcoming challenges or resisting negative situations

    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
    ittal
    -0.85
    etry
    -0.82
    nih
    -0.76
    人
    -0.76
    estial
    -0.76
    iband
    -0.73
    omet
    -0.73
    toc
    -0.72
    iatrics
    -0.69
    ograp
    -0.69
    POSITIVE LOGITS
     criticism
    1.03
     criticisms
    0.96
     dissent
    0.94
     incoming
    0.91
     pesky
    0.91
     boredom
    0.91
     objections
    0.89
     pests
    0.89
     temptation
    0.88
     accusations
    0.88
    Activations Density 0.173%

    No Known Activations