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. 2925
    Prev
    Next
    INDEX
    Explanations

    dates and events related to terrorist attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to the September 11 attacks and related events

    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
    æĢ
    -0.74
     Seller
    -0.74
     Tsuk
    -0.69
     Panasonic
    -0.69
    Featured
    -0.68
    Farm
    -0.68
     Marketable
    -0.67
    é¾įå
    -0.67
    Avg
    -0.66
     Somew
    -0.66
    POSITIVE LOGITS
     terror
    0.96
     hijacked
    0.94
     hij
    0.94
    ghazi
    0.91
     bombing
    0.90
     bombings
    0.87
     wre
    0.84
     assassination
    0.84
     bombers
    0.82
    dinand
    0.80
    Activations Density 0.103%

    No Known Activations