© 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. 20832
    Prev
    Next
    INDEX
    Explanations

    instances of legal actions or statements related to lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in."

    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
     %%
    -0.74
     learners
    -0.71
     inval
    -0.70
    soever
    -0.66
    edly
    -0.64
    izens
    -0.64
     hooks
    -0.63
     heirs
    -0.62
    /(
    -0.61
     inherit
    -0.61
    POSITIVE LOGITS
     lieu
    1.26
     favor
    1.19
     conjunction
    1.14
     accordance
    1.09
    ordinate
    1.07
     vain
    1.06
    patient
    1.06
     regards
    1.05
     order
    1.05
     vitro
    1.02
    Activations Density 0.623%

    No Known Activations