© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2295
    Prev
    Next
    INDEX
    Explanations

    advertisements within a text

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    various forms of advertisements and accompanying visual content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     manif
    -0.71
    cker
    -0.68
    ersen
    -0.67
    anu
    -0.66
     interchange
    -0.65
    icket
    -0.64
     inadvertently
    -0.64
    ensical
    -0.63
    ensibly
    -0.63
     diseng
    -0.63
    POSITIVE LOGITS
     ..........
    1.63
    ³³³
    0.92
    ..................
    0.89
     ......
    0.87
     ................
    0.86
     ³³
    0.85
    ãħĭãħĭ
    0.84
    ļéĨĴ
    0.83
    ¯¯¯¯¯¯¯¯
    0.82
     ........
    0.82
    Activations Density 0.004%

    No Known Activations