© 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. 6-RES-JB
    11. 10907
    Prev
    Next
    INDEX
    Explanations

    comparative words indicating a higher degree or level

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "more" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.73
    Rus
    -0.73
    UFC
    -0.72
    è¦ļéĨĴ
    -0.72
    ruary
    -0.72
    xtap
    -0.70
    adelphia
    -0.69
    Nation
    -0.69
    liest
    -0.68
     Dyn
    -0.68
    POSITIVE LOGITS
     than
    1.04
     stringent
    0.95
     manageable
    0.94
     adventurous
    0.92
     forgiving
    0.88
     inclined
    0.87
     subtle
    0.87
    than
    0.82
     sensible
    0.82
     len
    0.80
    Activations Density 0.062%

    No Known Activations