© 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. 9-RES-JB
    11. 14849
    Prev
    Next
    INDEX
    Explanations

    legal actions, such as lawsuits, appeals, petitions, and complaints

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal actions and lawsuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     symbolism
    -0.66
    oured
    -0.66
     sacrificed
    -0.65
     Palest
    -0.64
    peak
    -0.63
    seeing
    -0.62
     quot
    -0.62
     bestowed
    -0.61
     Ethiop
    -0.60
    mast
    -0.60
    POSITIVE LOGITS
     complaint
    1.29
     lawsuit
    1.17
     complaints
    1.07
     paperwork
    0.99
     lawsuits
    0.99
     petitions
    0.98
     petition
    0.98
     affidavit
    0.90
     grievance
    0.90
     papers
    0.90
    Activations Density 0.097%

    No Known Activations