© 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. 14124
    Prev
    Next
    INDEX
    Explanations

    phrases written in Spanish

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional states or sentiments

    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
    advertisement
    -0.80
    APH
    -0.78
    IAL
    -0.74
    advertising
    -0.74
    Wheel
    -0.72
    Mex
    -0.72
    ipal
    -0.71
    FB
    -0.70
    AX
    -0.70
    Enlarge
    -0.69
    POSITIVE LOGITS
     los
    0.89
     la
    0.87
     las
    0.79
     lang
    0.78
     bes
    0.77
     tha
    0.77
     vel
    0.75
     nos
    0.74
     wal
    0.69
     tul
    0.68
    Activations Density 0.126%

    No Known Activations