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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3818
    Prev
    Next
    INDEX
    Explanations

    locations in Eastern and Western regions

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical regions, specifically eastern and western areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bomb
    -0.90
    Fund
    -0.84
    LM
    -0.81
    iral
    -0.79
    BALL
    -0.76
    init
    -0.75
    Ver
    -0.75
    ARP
    -0.74
    Jump
    -0.74
    Account
    -0.74
    POSITIVE LOGITS
     shores
    0.77
     stuffing
    0.77
    querque
    0.77
    eston
    0.76
     western
    0.75
     hemisphere
    0.75
     waters
    0.74
     eastern
    0.73
     counties
    0.72
     Myanmar
    0.71
    Activations Density 0.010%

    No Known Activations