© 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. 10-RES-JB
    11. 11203
    Prev
    Next
    INDEX
    Explanations

    locations, especially related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.74
     pione
    -0.70
    æĸ¹
    -0.68
    aukee
    -0.64
    chel
    -0.62
    Percent
    -0.61
     ect
    -0.60
    AMP
    -0.60
     æľ
    -0.60
    rod
    -0.60
    POSITIVE LOGITS
    's
    1.39
    ÃŃs
    0.87
    't
    0.84
    're
    0.82
    ').
    0.81
    '
    0.77
    Returns
    0.76
    `
    0.75
    ']
    0.75
    'd
    0.75
    Activations Density 0.129%

    No Known Activations