© 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. 6862
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recently"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "recently."

    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
    eers
    -0.71
    sure
    -0.69
    plays
    -0.66
    feeding
    -0.65
     strictly
    -0.64
    amination
    -0.61
     tomorrow
    -0.60
    emen
    -0.60
     respect
    -0.59
    claimer
    -0.59
    POSITIVE LOGITS
     underwent
    1.05
     completed
    0.98
     unearthed
    0.94
     undergone
    0.94
     debuted
    0.93
     acquired
    0.92
     surpassed
    0.92
     departed
    0.92
     concluded
    0.90
     reopened
    0.90
    Activations Density 0.070%

    No Known Activations