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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8921
    Prev
    Next
    INDEX
    Explanations

    references to political figures and discussions related to intelligence reports

    oai_token-act-pair · gpt-3.5-turbo

    references to investigations or discussions related to foreign interference, particularly focusing on Russia and political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     CLR
    -0.89
     Slayer
    -0.86
     debtor
    -0.82
    uckland
    -0.80
     Auckland
    -0.78
    tnc
    -0.77
     welf
    -0.75
     glim
    -0.74
     Bombay
    -0.73
     Homeless
    -0.72
    POSITIVE LOGITS
     Nunes
    1.63
     Russia
    1.56
     Kremlin
    1.53
     Russians
    1.52
     Mueller
    1.49
     Russian
    1.46
     Putin
    1.45
    Russia
    1.45
     Comey
    1.44
    Russian
    1.42
    Activations Density 0.491%

    No Known Activations