© 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. 9-RES-JB
    11. 2957
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "phrase"

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases and slogans within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appointments
    -0.69
    DERR
    -0.69
    gur
    -0.68
     hemor
    -0.68
    aples
    -0.68
     Thro
    -0.65
    fman
    -0.65
    ockets
    -0.65
    rake
    -0.64
     Dise
    -0.63
    POSITIVE LOGITS
    phrase
    1.10
    ology
    1.08
     uttered
    0.96
    terday
    0.96
     phrase
    0.91
    stick
    0.86
     coined
    0.82
    witz
    0.82
     phrases
    0.82
    ciation
    0.81
    Activations Density 0.057%

    No Known Activations