© 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. 10305
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities, particularly Lady Gaga

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific celebrities, particularly Lady Gaga and Ariana Grande

    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
    ģ
    -0.86
    æ³
    -0.82
     Sod
    -0.72
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.72
     Icar
    -0.71
     Shinra
    -0.71
     Pax
    -0.71
     Noct
    -0.70
     Raiders
    -0.70
     Seaf
    -0.69
    POSITIVE LOGITS
    steen
    0.97
    udeau
    0.91
    hler
    0.89
    essen
    0.85
    awaru
    0.84
    psey
    0.83
    anooga
    0.82
     millenn
    0.81
     tremend
    0.76
     ende
    0.76
    Activations Density 0.020%

    No Known Activations