© 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. 7-RES-JB
    11. 23819
    Prev
    Next
    INDEX
    Explanations

    words that stand out or are emphasized in a text

    oai_token-act-pair · gpt-3.5-turbo

    mention of the word "words" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DERR
    -0.75
    izo
    -0.73
    ramid
    -0.72
    roxy
    -0.69
    enture
    -0.67
    olls
    -0.65
     cumbers
    -0.65
    ño
    -0.64
    romeda
    -0.63
     notor
    -0.63
    POSITIVE LOGITS
    mith
    1.54
     spoken
    1.11
     uttered
    1.03
     aloud
    0.89
    speak
    0.87
    press
    0.86
     words
    0.84
    poons
    0.82
    sworth
    0.82
    words
    0.78
    Activations Density 0.023%

    No Known Activations