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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 7984
    Prev
    Next
    INDEX
    Explanations

    mentions of suicide bombers

    oai_token-act-pair · gpt-3.5-turbo

    references to bombers and suicide bombers

    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
    laus
    -0.78
     Dise
    -0.74
     Pradesh
    -0.72
    ð
    -0.71
    UTC
    -0.69
    ãĤĭ
    -0.69
    oint
    -0.69
    KEY
    -0.68
    Nev
    -0.68
     Legends
    -0.66
    POSITIVE LOGITS
     bomber
    1.23
     bombers
    1.10
     bombing
    0.97
     detonated
    0.95
     Bomber
    0.86
     Bom
    0.84
     bombard
    0.80
     deton
    0.79
    selage
    0.79
     bombings
    0.77
    Activations Density 0.013%

    No Known Activations