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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7850
    Prev
    Next
    INDEX
    Explanations

    sentences indicating legal or formal language

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods

    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
     selfie
    -0.95
     unstoppable
    -0.88
     ditch
    -0.88
     hug
    -0.84
     unbeat
    -0.82
     tricked
    -0.81
     soar
    -0.80
     fearless
    -0.80
     ape
    -0.80
     invincible
    -0.79
    POSITIVE LOGITS
     Presumably
    1.46
     Certainly
    1.39
     Obviously
    1.33
     Consequently
    1.29
     However
    1.29
     Nonetheless
    1.29
     Therefore
    1.28
     Nevertheless
    1.27
     Accordingly
    1.27
     Generally
    1.27
    Activations Density 0.467%

    No Known Activations