© 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. 6-RES-JB
    11. 12875
    Prev
    Next
    INDEX
    Explanations

    mentions of women and children in various contexts, including medical and humanitarian situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of women and children in contexts of violence or conflict

    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
     Ames
    -0.86
    ooth
    -0.84
     Madison
    -0.76
     Hamilton
    -0.69
    Scot
    -0.68
     Scot
    -0.68
    Champ
    -0.68
    Marsh
    -0.67
     Spokane
    -0.67
     dime
    -0.67
    POSITIVE LOGITS
     evacuated
    0.90
     evacuate
    0.79
    pillar
    0.79
     ashore
    0.78
     Kurd
    0.76
    á¸
    0.75
     belonging
    0.75
    zl
    0.75
     Syri
    0.74
     Hezbollah
    0.74
    Activations Density 0.451%

    No Known Activations