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. 12311
    Prev
    Next
    INDEX
    Explanations

    keywords related to investigations and ties between political campaigns and foreign entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political collusion and foreign interference related to the Trump campaign and Russia

    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
     ç¥ŀ
    -0.83
     :(
    -0.81
     âĺ
    -0.79
    iku
    -0.77
     wip
    -0.72
     âĿ
    -0.70
    ciation
    -0.70
     Brend
    -0.69
     ðŁĻĤ
    -0.69
     :)
    -0.67
    POSITIVE LOGITS
     FBI
    1.18
     wiret
    1.15
     CIA
    1.13
     intelligence
    1.10
     dossier
    1.10
     intercepted
    1.08
     subpoen
    1.06
     incrim
    1.05
    FBI
    1.05
     FISA
    1.04
    Activations Density 1.453%

    No Known Activations