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. 11-RES-JB
    6. 8604
    Prev
    Next
    INDEX
    Explanations

    terms related to war and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to countries in conflict and the associated humanitarian crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basis
    -0.80
    OPLE
    -0.72
     breakfast
    -0.68
     decimal
    -0.68
     pencil
    -0.67
     Gifts
    -0.65
     decency
    -0.65
     finishes
    -0.65
     directives
    -0.65
     arts
    -0.65
    POSITIVE LOGITS
    prone
    1.71
    ridden
    1.62
    torn
    1.54
    inducing
    1.49
    resistant
    1.42
    laden
    1.41
    affected
    1.36
    induced
    1.34
    rav
    1.33
    filled
    1.26
    Activations Density 0.063%

    No Known Activations