© 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. 4-RES-JB
    11. 10530
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "Those."

    oai_token-act-pair · gpt-3.5-turbo

    the word "Those" at various activation intensities

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

    No Comments

    Negative Logits
    shapeshifter
    -0.82
    ILY
    -0.81
    ointment
    -0.75
    orate
    -0.74
     ..."
    -0.69
    irth
    -0.69
    zo
    -0.69
    Drag
    -0.67
    ½
    -0.67
    pless
    -0.67
    POSITIVE LOGITS
     wishing
    0.89
     pesky
    0.82
     kinds
    0.77
     interested
    0.77
     thoughts
    0.76
     voices
    0.74
     resear
    0.70
     interviewed
    0.70
     wanting
    0.67
     sorts
    0.67
    Activations Density 0.057%

    No Known Activations