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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9634
    Prev
    Next
    INDEX
    Explanations

    mentions of religious or social conflicts or tensions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sectarianism and communal violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llor
    -1.00
    mber
    -0.84
    reon
    -0.82
    OTAL
    -0.81
    thereum
    -0.77
    âĹ¼
    -0.77
    know
    -0.76
    olesterol
    -0.75
    cko
    -0.74
    cript
    -0.74
    POSITIVE LOGITS
     separ
    0.82
     divides
    0.79
     killings
    0.78
    ally
    0.78
     relations
    0.78
     divisions
    0.78
    ities
    0.76
    uled
    0.75
     massacres
    0.75
     rivalry
    0.75
    Activations Density 0.052%

    No Known Activations