© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18816
    Prev
    Next
    INDEX
    Explanations

    phrases with a strong emotional and decisive tone

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advoc
    -0.88
     millenn
    -0.85
     skelet
    -0.83
     disadvantage
    -0.83
     favourable
    -0.81
     carbohyd
    -0.80
     encount
    -0.79
     telesc
    -0.77
     warr
    -0.76
    ascus
    -0.76
    POSITIVE LOGITS
     Literally
    1.54
     And
    1.47
     Especially
    1.39
     Because
    1.38
     Everywhere
    1.32
     Period
    1.29
     Lots
    1.28
     That
    1.27
     Except
    1.26
     Twice
    1.25
    Activations Density 0.485%

    No Known Activations