© 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. 11488
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is speaking or expressing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of speech or quotations attributed to individuals

    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
    à¦
    -0.78
    irrel
    -0.75
    alysed
    -0.74
    Ò
    -0.73
    Synopsis
    -0.73
    pee
    -0.73
    SourceFile
    -0.73
    ãĥİ
    -0.72
    Ãł
    -0.72
    aceae
    -0.71
    POSITIVE LOGITS
     he
    0.93
     there
    0.93
     they
    0.81
     it
    0.79
     although
    0.78
     technicians
    0.77
     investigators
    0.75
    adays
    0.73
     afterward
    0.73
     that
    0.72
    Activations Density 0.168%

    No Known Activations