© 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. 18642
    Prev
    Next
    INDEX
    Explanations

    phrases involving things or events that have never happened before

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetition or prior experiences that have never occurred before

    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
     warranties
    -0.58
     tomorrow
    -0.57
    ))))
    -0.56
     Tomorrow
    -0.56
    may
    -0.55
     guesses
    -0.53
     )))
    -0.52
     2019
    -0.52
    redients
    -0.52
     summarizes
    -0.52
    POSITIVE LOGITS
     nor
    1.12
     before
    0.98
     anywhere
    0.95
     EVER
    0.86
     since
    0.84
     professionally
    0.83
     firsthand
    0.81
    before
    0.80
     BEFORE
    0.78
    ever
    0.76
    Activations Density 0.373%

    No Known Activations