© 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. 14493
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific name "Bartlett"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Bart."

    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
    istors
    -0.66
    ciation
    -0.66
    WARD
    -0.65
    VEN
    -0.63
    FER
    -0.63
    ulton
    -0.63
    itures
    -0.63
    TPPStreamerBot
    -0.62
    terday
    -0.60
     butterflies
    -0.59
    POSITIVE LOGITS
    lett
    0.98
    ric
    0.98
    ram
    0.91
    rys
    0.91
    oken
    0.90
    olini
    0.90
    rip
    0.87
    esian
    0.87
    hel
    0.85
    lest
    0.84
    Activations Density 0.022%

    No Known Activations