© 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. 11-RES-JB
    11. 12561
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and actions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases indicating conditional or causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered 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
    •Causality
    Because + so,therefore

    No Comments

    Negative Logits
    SourceFile
    -0.80
    Detailed
    -0.74
    kefeller
    -0.74
    Report
    -0.72
    azeera
    -0.65
    姫
    -0.64
    æ©
    -0.64
    externalActionCode
    -0.63
    ãĥĥãĥĪ
    -0.62
    Explore
    -0.62
    POSITIVE LOGITS
     my
    1.47
     I
    1.42
     myself
    1.12
     My
    0.98
     mine
    0.91
     MY
    0.90
     lately
    0.89
     whenever
    0.89
     blogging
    0.86
     waking
    0.85
    Activations Density 0.418%

    No Known Activations