© 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. 0-RES-JB
    6. 19297
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to legal actions or proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pole
    -0.78
     runway
    -0.66
     taught
    -0.65
     handic
    -0.65
     machine
    -0.64
     suff
    -0.64
     plateau
    -0.63
     cripp
    -0.63
     roof
    -0.61
     nursery
    -0.60
    POSITIVE LOGITS
    actions
    4.42
    action
    2.88
    ACTION
    2.11
    acting
    1.76
    acted
    1.73
    acts
    1.73
    activity
    1.48
     Actions
    1.41
    actor
    1.38
    act
    1.35
    Activations Density 0.019%

    No Known Activations