© 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. 17563
    Prev
    Next
    INDEX
    Explanations

    phrases containing quotes from people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "said" in various contexts

    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
    isable
    -0.70
    earances
    -0.66
    peat
    -0.62
    cles
    -0.59
    mia
    -0.58
    phia
    -0.57
    iencies
    -0.56
    illions
    -0.56
    scribe
    -0.56
    pes
    -0.56
    POSITIVE LOGITS
     sarcast
    1.07
    âĢ
    0.99
    .?
    0.97
    .�
    0.95
    .
    0.90
     âĢ
    0.90
    .–
    0.89
    .<
    0.88
     aloud
    0.85
    .(
    0.84
    Activations Density 0.138%

    No Known Activations