© 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. 9-RES-JB
    11. 18476
    Prev
    Next
    INDEX
    Explanations

    instances of the word "such"

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases emphasizing the term "such."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emale
    -0.83
    ellen
    -0.81
    otta
    -0.80
    uay
    -0.79
    hene
    -0.76
    eric
    -0.76
    maxwell
    -0.75
    opian
    -0.75
    allo
    -0.74
    rik
    -0.73
    POSITIVE LOGITS
     establishments
    0.91
     endeavors
    0.90
     drastic
    0.89
     sentiments
    0.89
     matters
    0.88
     tactics
    0.87
     things
    0.86
     phenomena
    0.85
     considerations
    0.85
     incidents
    0.85
    Activations Density 0.052%

    No Known Activations