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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 7633
    Prev
    Next
    INDEX
    Explanations

    words related to conquest and domination

    oai_token-act-pair · gpt-3.5-turbo

    references to themes of domination and conquest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clos
    -0.68
    Recommend
    -0.67
     explan
    -0.67
     transplant
    -0.67
    affer
    -0.66
     conduc
    -0.66
     incorpor
    -0.66
    hift
    -0.65
    heter
    -0.64
     coh
    -0.64
    POSITIVE LOGITS
     conquered
    0.95
     territories
    0.90
     conquest
    0.89
    ãĤ¨ãĥ«
    0.85
    ãĥ¯
    0.84
    illes
    0.81
     Normandy
    0.79
     conquer
    0.78
     Territories
    0.78
    oise
    0.77
    Activations Density 0.046%

    No Known Activations