© 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. 6-RES-JB
    11. 1495
    Prev
    Next
    INDEX
    Explanations

    names of locations or places, specifically focusing on the city of Yangon

    oai_token-act-pair · gpt-3.5-turbo

    references to the location and context of Yangon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.73
    ively
    -0.71
    hered
    -0.71
    byter
    -0.71
    rees
    -0.71
    kefeller
    -0.70
    rodu
    -0.70
    ngth
    -0.69
    IVE
    -0.67
    essions
    -0.67
    POSITIVE LOGITS
    lda
    1.00
     Yang
    0.96
    gang
    0.93
     Xiao
    0.90
    yang
    0.90
    jiang
    0.89
    Yang
    0.84
     Jian
    0.79
     Uz
    0.78
    jing
    0.77
    Activations Density 0.024%

    No Known Activations