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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17754
    Prev
    Next
    INDEX
    Explanations

    comments within a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize civil discourse and respectful communication

    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
    iffe
    -0.88
     Crus
    -0.78
     Hamp
    -0.77
     Fal
    -0.77
    anchester
    -0.74
     Ramsay
    -0.74
     semin
    -0.73
    anza
    -0.73
     Salvation
    -0.73
    uala
    -0.71
    POSITIVE LOGITS
     Smart
    2.38
    Smart
    2.34
    smart
    2.06
     smart
    2.04
     smarter
    1.52
     Intelligent
    1.38
     smartest
    1.31
     intelligent
    1.23
    elligent
    1.14
     Clever
    1.14
    Activations Density 0.117%

    No Known Activations