© 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. 11-RES-JB
    11. 12815
    Prev
    Next
    INDEX
    Explanations

    sentences ending with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    sentences or statements that express finality or conclusions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     millenn
    -1.05
     encount
    -0.92
     challeng
    -0.89
     advoc
    -0.88
     favourable
    -0.88
    ancies
    -0.86
     warr
    -0.85
     carbohyd
    -0.85
     disadvantage
    -0.84
     suspic
    -0.83
    POSITIVE LOGITS
     Literally
    1.60
     Because
    1.44
     And
    1.41
     Seriously
    1.36
     Except
    1.35
     Period
    1.35
     Especially
    1.30
     Nope
    1.28
     Absolutely
    1.28
     Lots
    1.27
    Activations Density 0.435%

    No Known Activations