© 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. 2899
    Prev
    Next
    INDEX
    Explanations

    mentions of confidential documents or memos

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "memo."

    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
    reek
    -0.72
    Interstitial
    -0.67
     Fen
    -0.66
    tool
    -0.65
    ulia
    -0.64
    lihood
    -0.64
    gpu
    -0.63
     Greeks
    -0.63
    Georgia
    -0.62
    effic
    -0.62
    POSITIVE LOGITS
     memo
    1.08
    andum
    1.03
     memos
    0.96
    ovie
    0.84
    ographed
    0.82
    isode
    0.80
    ariat
    0.78
    osal
    0.78
    aires
    0.76
    velop
    0.76
    Activations Density 0.017%

    No Known Activations