© 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. 6947
    Prev
    Next
    INDEX
    Explanations

    synonyms or related terms for words related to law and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" in contexts related to important issues or truths

    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
    results
    -0.70
     pressures
    -0.68
     flashes
    -0.67
    etsk
    -0.67
     alerts
    -0.66
    cards
    -0.66
     associations
    -0.66
     descriptions
    -0.65
     shakes
    -0.65
     hybrids
    -0.64
    POSITIVE LOGITS
     longstanding
    1.09
     cherished
    1.04
     loophole
    1.03
     portion
    1.03
     crucial
    1.00
     previously
    0.96
     hitherto
    0.94
     handful
    0.93
     vital
    0.90
     swath
    0.90
    Activations Density 0.212%

    No Known Activations