© 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. 2-RES-JB
    11. 5429
    Prev
    Next
    INDEX
    Explanations

    references to acts or discussions related to genocide

    oai_token-act-pair · gpt-3.5-turbo

    mentions of genocide

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.84
    PATH
    -0.77
    Lago
    -0.76
    alg
    -0.72
    aton
    -0.72
    body
    -0.71
    Lear
    -0.70
     Eucl
    -0.68
    sol
    -0.66
    atum
    -0.65
    POSITIVE LOGITS
     genocide
    1.30
     Genocide
    1.14
    ocide
    0.99
    ãĥ¼ãĥĨãĤ£
    0.93
     Rwanda
    0.87
     massacres
    0.86
     atrocities
    0.86
    ãĤº
    0.83
     massacre
    0.82
     massac
    0.81
    Activations Density 0.019%

    No Known Activations