© 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. 4-RES-JB
    11. 17056
    Prev
    Next
    INDEX
    Explanations

    verbs related to legal actions and government procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and regulatory discussions

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

    No Comments

    Negative Logits
    etimes
    -0.57
    space
    -0.53
    scar
    -0.50
    caps
    -0.50
     Sung
    -0.48
     ILCS
    -0.48
    hello
    -0.47
     Soph
    -0.47
    cell
    -0.47
    oos
    -0.46
    POSITIVE LOGITS
     appoint
    0.66
     promulg
    0.54
     appointing
    0.54
     franch
    0.52
     approving
    0.51
    £
    0.50
     reimb
    0.50
     its
    0.50
     NAFTA
    0.50
    âĸij
    0.49
    Activations Density 1.496%

    No Known Activations