© 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. 729
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "According to a report released by" or similar phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "by."

    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
    chwitz
    -0.75
     brakes
    -0.72
    ivia
    -0.70
    hene
    -0.69
     manif
    -0.69
    bler
    -0.68
    gage
    -0.68
    uality
    -0.67
    ãĤ£
    -0.67
    hement
    -0.65
    POSITIVE LOGITS
     virtue
    1.03
    laws
    0.85
    products
    0.84
    product
    0.75
     statute
    0.73
    pass
    0.71
     Forbes
    0.70
     citing
    0.70
    law
    0.69
     Voices
    0.67
    Activations Density 0.153%

    No Known Activations