© 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. 2-RES-JB
    11. 11607
    Prev
    Next
    INDEX
    Explanations

    words related to 'didn't' or 'don't'

    oai_token-act-pair · gpt-3.5-turbo

    the word "didn't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dise
    -0.84
    armed
    -0.74
     DRAGON
    -0.70
     Duty
    -0.66
     VERS
    -0.64
     Enemies
    -0.63
     Mant
    -0.63
    upp
    -0.63
     Methods
    -0.62
     Ivory
    -0.61
    POSITIVE LOGITS
    't
    1.39
    nt
    0.86
    ":"/
    0.84
    ajor
    0.78
    etsk
    0.75
    ijah
    0.73
    okia
    0.72
     indeed
    0.71
    ema
    0.71
    ÃŃ
    0.70
    Activations Density 0.034%

    No Known Activations