Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3134
    Prev
    Next
    INDEX
    Explanations

    phrases denoting importance, significance, or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize particular importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.74
    cli
    -0.73
     guiActive
    -0.71
     essentially
    -0.71
    only
    -0.70
    ensibly
    -0.69
     merely
    -0.68
    both
    -0.68
    ences
    -0.67
    ylon
    -0.67
    POSITIVE LOGITS
     egregious
    1.22
     noteworthy
    1.04
     poignant
    0.99
     troublesome
    0.97
     gall
    0.95
     vulnerable
    0.94
     suited
    0.93
     acute
    0.91
     notable
    0.90
     worrisome
    0.90
    Activations Density 0.040%

    No Known Activations