© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    the word "final."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "final" in various contexts

    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
    hemy
    -0.71
    luster
    -0.67
    velt
    -0.65
    afort
    -0.65
    gypt
    -0.64
    kun
    -0.63
    asus
    -0.62
    then
    -0.61
    zee
    -0.60
    ensional
    -0.60
    POSITIVE LOGITS
     straw
    1.02
     touches
    0.96
    izing
    0.92
    izers
    0.92
     tally
    0.91
     installment
    0.91
     stages
    0.90
     hurdle
    0.89
     curtain
    0.88
     showdown
    0.88
    Activations Density 0.036%

    No Known Activations