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. 10583
    Prev
    Next
    INDEX
    Explanations

    mentions of ceasefire agreements and related terms in conflicts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ceasefires in conflict contexts

    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
    amera
    -0.71
    mson
    -0.70
     Walton
    -0.69
    nery
    -0.68
     skew
    -0.66
    osaurus
    -0.64
    jit
    -0.64
     Fowler
    -0.64
    ãĤ¨ãĥ«
    -0.64
    rors
    -0.64
    POSITIVE LOGITS
     negotiated
    1.26
     treaty
    1.22
     Pact
    1.20
     ceasefire
    1.15
     negotiations
    1.15
     pact
    1.15
     Agreement
    1.13
     accord
    1.13
     Talks
    1.12
     Treaty
    1.11
    Activations Density 0.307%

    No Known Activations