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. 12-RES-JB
    6. 15058
    Prev
    Next
    INDEX
    Explanations

    references to the terrorist group Al Qaeda

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of Al-Qaeda or its affiliates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     doubling
    -0.59
     firsthand
    -0.56
     uniquely
    -0.55
     permanently
    -0.55
    ALLY
    -0.54
     redund
    -0.54
     bottleneck
    -0.53
     goodbye
    -0.52
     redesign
    -0.52
     thousands
    -0.52
    POSITIVE LOGITS
     Qaeda
    1.19
    aw
    1.01
    awi
    0.97
    Qaeda
    0.96
     Jazeera
    0.95
    Qaida
    0.87
    bu
    0.81
     Houth
    0.80
    uminium
    0.79
    amo
    0.76
    Activations Density 0.026%

    No Known Activations