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. 19176
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and locations in the Philippines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical locations 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
    Weiss
    -1.06
     Weiss
    -1.01
     Somerset
    -0.92
     Sabbath
    -0.89
     Hess
    -0.87
     Wheat
    -0.87
     Yorkshire
    -0.85
     Sheffield
    -0.85
    Wisconsin
    -0.85
     Bolton
    -0.84
    POSITIVE LOGITS
     Duterte
    2.28
     Philippine
    2.16
     Filipino
    2.12
     Manila
    2.09
     Philippines
    2.00
    uterte
    1.95
     Filip
    1.86
     Marcos
    1.70
     Rodrigo
    1.50
    Philipp
    1.49
    Activations Density 0.312%

    No Known Activations