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. 17560
    Prev
    Next
    INDEX
    Explanations

    references to the terrorist organization Al-Qaeda

    oai_token-act-pair · gpt-3.5-turbo

    references to the organization Al-Qaeda

    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
     Gron
    -0.90
     Seah
    -0.84
     Wald
    -0.77
     Hubble
    -0.74
    ðĿ
    -0.74
     WD
    -0.72
     Brun
    -0.71
     Marvel
    -0.71
     Goodell
    -0.71
     Veh
    -0.71
    POSITIVE LOGITS
    aeda
    1.01
     affiliates
    0.97
    istani
    0.96
     terrorists
    0.95
     insurgents
    0.91
     bombings
    0.90
     affiliated
    0.88
     affiliate
    0.87
     operatives
    0.87
    Qaeda
    0.86
    Activations Density 0.019%

    No Known Activations