© 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. 9-RES-JB
    11. 24311
    Prev
    Next
    INDEX
    Explanations

    first person statements indicating that something is the best or has never been equaled

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ever" used to emphasize experiences or occurrences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Axel
    -0.68
    OUR
    -0.66
     Bav
    -0.65
     Chop
    -0.64
    VD
    -0.63
     Azerbai
    -0.63
    emia
    -0.63
     Baz
    -0.61
     Kub
    -0.59
    /+
    -0.59
    POSITIVE LOGITS
    theless
    1.19
    deen
    0.89
    bilt
    0.86
     doubted
    0.79
     heard
    0.78
     dreamed
    0.78
    igslist
    0.78
     wanted
    0.76
     wished
    0.76
     cared
    0.75
    Activations Density 0.043%

    No Known Activations