© 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. 17635
    Prev
    Next
    INDEX
    Explanations

    words related to enhancing or completing something

    oai_token-act-pair · gpt-3.5-turbo

    the word "complement" and its variations

    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
     Tycoon
    -0.78
    cients
    -0.71
    gear
    -0.69
    Lot
    -0.66
    ylene
    -0.66
    anyl
    -0.66
    rant
    -0.64
    psy
    -0.63
     blat
    -0.63
    ves
    -0.63
    POSITIVE LOGITS
     complement
    1.31
    xual
    1.09
     compliment
    1.03
     compliments
    0.89
    isson
    0.85
    ement
    0.81
    ":[{"
    0.80
     complementary
    0.78
    issance
    0.78
    uple
    0.75
    Activations Density 0.017%

    No Known Activations