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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 9172
    Prev
    Next
    INDEX
    Explanations

    controversial or negative situations or events

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases indicating argumentation or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    operator
    -0.85
    ãĥij
    -0.79
    crow
    -0.78
     guiActiveUnfocused
    -0.77
    worm
    -0.77
     XD
    -0.77
    breaker
    -0.76
    ractor
    -0.76
    Fax
    -0.76
    SourceFile
    -0.74
    POSITIVE LOGITS
     democracies
    1.24
     neoliberal
    1.23
     policymakers
    1.19
     populism
    1.19
     progressives
    1.18
     globalization
    1.15
     majorities
    1.11
     populist
    1.10
     nationalism
    1.09
     governments
    1.08
    Activations Density 0.396%

    No Known Activations