© 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. 3-RES-JB
    11. 17128
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rizzo"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "izz"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cowardly
    -0.70
     pity
    -0.69
     mutual
    -0.66
     pride
    -0.66
     civilization
    -0.65
     immersion
    -0.65
    sighted
    -0.65
     sanctuary
    -0.64
     erect
    -0.64
     wills
    -0.64
    POSITIVE LOGITS
    azz
    1.30
    izz
    1.16
    arro
    1.11
    arella
    1.02
    etta
    0.99
    agate
    0.97
    ipedia
    0.96
    ombie
    0.93
    arre
    0.92
    aret
    0.91
    Activations Density 0.009%

    No Known Activations