© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3017
    Prev
    Next
    INDEX
    Explanations

    mentions of Indian political figures

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and figures in spiritual and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Weiss
    -0.68
     Zurich
    -0.66
    Mex
    -0.66
    lando
    -0.65
    gerald
    -0.64
    furt
    -0.64
    Miami
    -0.63
     webs
    -0.63
     french
    -0.63
     Brittany
    -0.63
    POSITIVE LOGITS
     Singh
    1.29
     Sabha
    1.27
     Sharma
    1.26
     Kumar
    1.19
     Yad
    1.16
     Gandhi
    1.14
     Patel
    1.11
     Gupta
    1.10
     Rao
    1.10
     Bhar
    1.09
    Activations Density 0.255%

    No Known Activations