© 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. 2-RES-JB
    11. 23259
    Prev
    Next
    INDEX
    Explanations

    mentions of Indian states, specifically Pradesh, with a stronger focus on Uttar Pradesh

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Andhra Pradesh and related geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.83
    Oracle
    -0.75
     Horton
    -0.70
    fts
    -0.68
    apsed
    -0.66
    avery
    -0.64
    osures
    -0.63
    ears
    -0.63
    ãĤ¤
    -0.62
    urtle
    -0.61
    POSITIVE LOGITS
     Pradesh
    1.65
     Bihar
    0.94
     Nadu
    0.89
     crore
    0.88
     Punjab
    0.87
     Territories
    0.85
     Tanz
    0.81
    igans
    0.80
     Railway
    0.79
     Sharma
    0.78
    Activations Density 0.008%

    No Known Activations