© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9787
    Prev
    Next
    INDEX
    Explanations

    words related to legal cases and individuals, particularly those involving the surname "Zimmer" or "Zar."

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to specific individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pett
    -0.78
    Interstitial
    -0.71
    luent
    -0.68
    croft
    -0.68
    eredith
    -0.66
    IVE
    -0.66
     Lauder
    -0.64
    itures
    -0.64
    æĦ
    -0.63
    uctor
    -0.63
    POSITIVE LOGITS
    ombies
    1.03
    ombie
    0.96
    zag
    0.85
    orah
    0.85
    ewski
    0.85
    ebra
    0.84
    geist
    0.81
    hao
    0.79
    iggurat
    0.79
    ealous
    0.77
    Activations Density 0.074%

    No Known Activations