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. 11-RES-JB
    6. 20421
    Prev
    Next
    INDEX
    Explanations

    names of leaders or figures related to a specific geopolitical context

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and events related to the Libyan conflict

    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
    Seattle
    -1.26
    âĢķ
    -1.02
     Ballard
    -1.00
     Bowman
    -0.99
    à¨
    -0.96
    Elsa
    -0.96
     Seattle
    -0.96
    à©
    -0.95
     Seahawks
    -0.93
     Blackhawks
    -0.93
    POSITIVE LOGITS
     Gaddafi
    2.35
     Libyan
    2.33
     Tripoli
    2.32
     Libya
    2.27
    addafi
    1.83
     Benghazi
    1.79
    Lib
    1.75
     Tunis
    1.72
     Tunisia
    1.64
    ghazi
    1.51
    Activations Density 0.261%

    No Known Activations