© 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. 7-RES-JB
    11. 4394
    Prev
    Next
    INDEX
    Explanations

    words related to supremacy or royalty

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with dominance or superiority

    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
     Aid
    -0.69
    earcher
    -0.68
    arf
    -0.68
     Ads
    -0.66
    ylene
    -0.66
     ABE
    -0.64
    ©¶æ
    -0.63
     Survivors
    -0.63
    iotics
    -0.63
     Farmers
    -0.61
    POSITIVE LOGITS
     jewel
    0.81
     jewels
    0.76
     pinnacle
    0.75
     ç¥ŀ
    0.75
    fal
    0.74
     grin
    0.73
    xon
    0.73
    liness
    0.73
    pieces
    0.73
     trove
    0.73
    Activations Density 0.149%

    No Known Activations