© 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. 11-RES-JB
    11. 8624
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishing norms or examples

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to setting standards, examples, or precedents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.69
    ugg
    -0.66
    orge
    -0.66
    leness
    -0.65
    jug
    -0.63
     Sunder
    -0.62
    jj
    -0.59
     compr
    -0.59
     outweigh
    -0.59
    ér
    -0.59
    POSITIVE LOGITS
     precedent
    1.28
     tone
    1.11
     precedence
    1.03
    tle
    1.00
     benchmark
    0.99
    flame
    0.98
     example
    0.94
     benchmarks
    0.94
     preced
    0.93
     record
    0.93
    Activations Density 0.061%

    No Known Activations