Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1774
    Prev
    Next
    INDEX
    Explanations

    words related to geographical poles

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic poles or pole-like concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¹
    -1.00
    Interstitial
    -0.87
    Export
    -0.87
    esis
    -0.78
    ebook
    -0.78
    HR
    -0.77
    ITNESS
    -0.77
    iencies
    -0.74
    ADRA
    -0.74
    VERTIS
    -0.73
    POSITIVE LOGITS
     pole
    1.43
     poles
    1.22
    pole
    1.12
     Pole
    1.02
    mic
    0.91
     Poles
    0.88
     maiden
    0.80
    ball
    0.76
    abases
    0.75
     dancer
    0.73
    Activations Density 0.013%

    No Known Activations