© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 7716
    Prev
    Next
    INDEX
    Explanations

    the word "shout" at varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shout" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.85
    insula
    -0.78
    urrency
    -0.72
     MFT
    -0.67
    omaly
    -0.67
    ologne
    -0.66
    emetery
    -0.65
    rost
    -0.65
    flix
    -0.64
    uton
    -0.64
    POSITIVE LOGITS
     shout
    1.07
     louder
    1.01
     aloud
    0.95
     shouted
    0.90
     shouts
    0.90
     loudly
    0.86
     yells
    0.83
    casters
    0.81
     slogans
    0.80
     shouting
    0.77
    Activations Density 0.010%

    No Known Activations