© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 1733
    Prev
    Next
    INDEX
    Explanations

    words that contain the sequence "que"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "que."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.70
     STATS
    -0.69
    lessly
    -0.68
    inately
    -0.67
    uania
    -0.65
    ERAL
    -0.65
    ITAL
    -0.63
    é¾įå
    -0.62
     glim
    -0.62
    wcsstore
    -0.61
    POSITIVE LOGITS
    que
    1.17
    ophon
    0.86
    edo
    0.83
    oking
    0.80
    erness
    0.80
    zon
    0.80
    xit
    0.79
    ques
    0.79
    aque
    0.78
    ge
    0.76
    Activations Density 0.009%

    No Known Activations