© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 984
    Prev
    Next
    INDEX
    Explanations

    social media platform names

    oai_token-act-pair · gpt-3.5-turbo

    references to popular social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samar
    -0.74
    orem
    -0.69
    ersen
    -0.68
    ORGE
    -0.68
     guiName
    -0.67
    Bey
    -0.67
     Lauder
    -0.65
    annis
    -0.65
    erella
    -0.63
    izoph
    -0.62
    POSITIVE LOGITS
    facebook
    0.71
    Ĥİ
    0.68
     Sina
    0.64
     Hacker
    0.64
    Tumblr
    0.64
    grounds
    0.64
    ĨĴ
    0.63
    ®
    0.63
    Joined
    0.62
    IJ
    0.61
    Activations Density 0.064%

    No Known Activations