© 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. 10-RES-JB
    11. 11238
    Prev
    Next
    INDEX
    Explanations

    words with the letters "th" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "th."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mechdragon
    -0.67
    fman
    -0.64
     hospitality
    -0.63
    ãĤ«
    -0.61
     Petraeus
    -0.60
    ITED
    -0.59
     vou
    -0.59
    姫
    -0.58
    worthiness
    -0.58
    VICE
    -0.58
    POSITIVE LOGITS
    umbnails
    1.28
    ieving
    1.24
    orns
    1.24
    ursday
    1.22
    umping
    1.21
    istle
    1.16
    uggish
    1.12
    irteen
    1.10
    aum
    1.10
    imble
    1.09
    Activations Density 0.011%

    No Known Activations