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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7115
    Prev
    Next
    INDEX
    Explanations

    phrases related to war and military operations in cities

    oai_token-act-pair · gpt-3.5-turbo

    references to cities in conflict zones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scot
    -0.91
    Lear
    -0.91
    wcsstore
    -0.77
    Reviewer
    -0.77
    Leary
    -0.76
    Recipe
    -0.74
     Mercury
    -0.74
    ONEY
    -0.72
     Richie
    -0.69
    Stud
    -0.67
    POSITIVE LOGITS
     Idlib
    1.20
     Aleppo
    1.10
     Raqqa
    1.04
     Homs
    1.03
     Mosul
    0.99
     Donetsk
    0.99
     outskirts
    0.97
    qqa
    0.96
     Abbas
    0.95
     mosques
    0.94
    Activations Density 0.210%

    No Known Activations