Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19456
    Prev
    Next
    INDEX
    Explanations

    mentions of genocides

    oai_token-act-pair · gpt-3.5-turbo

    references to genocide and discussions related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hawth
    -0.79
    aic
    -0.78
    lis
    -0.77
     Firm
    -0.76
     Quality
    -0.72
     Weld
    -0.69
     Benson
    -0.68
    biz
    -0.68
     Mason
    -0.67
    Store
    -0.66
    POSITIVE LOGITS
     genocide
    3.16
     Genocide
    2.63
     famine
    2.26
     extermination
    1.99
     starvation
    1.79
     massacres
    1.70
     amnesty
    1.70
     extinction
    1.67
     atrocities
    1.65
    ocide
    1.63
    Activations Density 0.033%

    No Known Activations