© 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. 3-RES-JB
    11. 581
    Prev
    Next
    INDEX
    Explanations

    the word "huge" at various levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "huge" and related terms

    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
    merce
    -0.70
    nington
    -0.67
     illum
    -0.67
    practice
    -0.67
    pring
    -0.67
    netflix
    -0.65
     Colony
    -0.62
     sidel
    -0.62
    puter
    -0.61
    ovember
    -0.61
    POSITIVE LOGITS
    uge
    1.16
    glers
    0.91
    llo
    0.82
    UGE
    0.81
     Refugee
    0.76
    gery
    0.76
    gest
    0.74
    utsche
    0.73
    yre
    0.73
    ãĥ¼ãĥĨãĤ£
    0.71
    Activations Density 0.011%

    No Known Activations