© 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. 1-RES-JB
    11. 3715
    Prev
    Next
    INDEX
    Explanations

    words related to corporate punishment

    oai_token-act-pair · gpt-3.5-turbo

    references to corporate punishment and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.84
    draft
    -0.74
     Famous
    -0.70
     Mayo
    -0.69
     Heard
    -0.67
    lihood
    -0.66
    BOOK
    -0.65
     Yellowstone
    -0.65
     Dill
    -0.65
    lde
    -0.65
    POSITIVE LOGITS
     corpor
    1.34
     mathemat
    1.14
    ately
    1.04
    abulary
    1.01
     glim
    1.01
    iform
    0.99
    escent
    0.98
     Corpor
    0.95
    iple
    0.94
    porate
    0.93
    Activations Density 0.005%

    No Known Activations