© 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. 17145
    Prev
    Next
    INDEX
    Explanations

    phrases related to enhancement or improvement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more" indicative of an emphasis on quantity or improvement

    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
    liest
    -0.79
    gee
    -0.70
    heid
    -0.69
    xtap
    -0.69
     Procedure
    -0.67
    been
    -0.66
     1979
    -0.63
    DragonMagazine
    -0.63
     Springer
    -0.62
     Translation
    -0.61
    POSITIVE LOGITS
     than
    1.10
     efficient
    0.96
     stringent
    0.93
     aggressive
    0.90
     manageable
    0.90
     meaningful
    0.88
     mature
    0.87
     equitable
    0.85
     expensive
    0.84
     realistic
    0.84
    Activations Density 0.149%

    No Known Activations