© 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. 8-RES-JB
    11. 541
    Prev
    Next
    INDEX
    Explanations

    legal terms and court-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that indicate the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     citiz
    -0.77
    etheless
    -0.71
    aterasu
    -0.69
    lihood
    -0.67
     prosec
    -0.67
    uph
    -0.65
     seiz
    -0.65
    assad
    -0.63
     Machina
    -0.62
    eness
    -0.61
    POSITIVE LOGITS
    WASHINGTON
    0.96
    Interested
    0.91
    Specifically
    0.86
    According
    0.84
    Amid
    0.82
    ³³³³³³³³
    0.81
    Speaking
    0.78
    Yesterday
    0.77
    ³³³³
    0.76
    Officials
    0.75
    Activations Density 0.173%

    No Known Activations