© 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. 23087
    Prev
    Next
    INDEX
    Explanations

    terms related to mills, bills, and related words

    oai_token-act-pair · gpt-3.5-turbo

    words related to "mills" or similar terms

    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
     IEEE
    -0.73
    ---------
    -0.68
    quel
    -0.68
    enegger
    -0.66
    apore
    -0.66
    puter
    -0.66
    OTHER
    -0.65
    linux
    -0.61
     Sigma
    -0.60
    Ô
    -0.60
    POSITIVE LOGITS
    uminati
    1.03
    iard
    0.99
    espie
    0.95
    sburg
    0.84
    bury
    0.78
    enthal
    0.76
    avascript
    0.76
    inger
    0.72
    imentary
    0.71
    creen
    0.70
    Activations Density 0.034%

    No Known Activations