© 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. 6871
    Prev
    Next
    INDEX
    Explanations

    references to the country "India."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "India."

    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
    ilts
    -0.74
    cies
    -0.74
    iaries
    -0.74
    yles
    -0.74
    ording
    -0.73
    otine
    -0.73
    esters
    -0.73
     Kessler
    -0.72
     McDonnell
    -0.71
    mble
    -0.71
    POSITIVE LOGITS
    apolis
    0.99
     Pradesh
    0.88
     Sharma
    0.87
     ru
    0.85
     Pv
    0.82
     Kumar
    0.82
     Rao
    0.82
    arta
    0.79
    India
    0.79
    endra
    0.77
    Activations Density 0.039%

    No Known Activations