© 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. 8-RES-JB
    11. 13124
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to media companies and services

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and apostrophes, indicating sentence endings or possessive forms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     showers
    -0.70
     detail
    -0.70
     Templ
    -0.66
     contrace
    -0.65
     polyg
    -0.65
     Leilan
    -0.63
     Indones
    -0.62
    oresc
    -0.61
     lapse
    -0.61
     thrill
    -0.60
    POSITIVE LOGITS
    til
    1.24
    Interstitial
    1.10
    Cause
    1.07
    Mech
    1.02
    cause
    0.92
    tis
    0.91
    s
    0.90
    taboola
    0.89
    arak
    0.87
    ses
    0.86
    Activations Density 0.043%

    No Known Activations