© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 16444
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    significant terms and phrases related to international criminal law and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    áµ
    -0.83
    natureconservancy
    -0.76
     Sears
    -0.70
    uci
    -0.70
     $$
    -0.69
    adelphia
    -0.68
     contrace
    -0.67
    visors
    -0.67
     Dickinson
    -0.67
     Owner
    -0.66
    POSITIVE LOGITS
     extrad
    1.64
     extradition
    1.61
     prosecution
    1.35
     prosecutions
    1.33
     indictment
    1.30
    Prosecutors
    1.25
     trials
    1.25
     confessions
    1.24
     sentenced
    1.24
     convict
    1.23
    Activations Density 0.532%

    No Known Activations