© 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. 4-RES-JB
    11. 10681
    Prev
    Next
    INDEX
    Explanations

    words related to geographical poles

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical poles

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

    No Comments

    Negative Logits
    æĸ¹
    -0.96
    Interstitial
    -0.85
    Export
    -0.83
    esis
    -0.81
    ebook
    -0.79
    enegger
    -0.74
    HR
    -0.74
    VERTIS
    -0.74
    ERAL
    -0.74
    ez
    -0.73
    POSITIVE LOGITS
     pole
    1.51
     poles
    1.30
    pole
    1.17
     Pole
    1.14
     Poles
    0.92
     maiden
    0.81
    mic
    0.80
     dancer
    0.75
     weld
    0.72
     pedest
    0.71
    Activations Density 0.008%

    No Known Activations