© 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. 9891
    Prev
    Next
    INDEX
    Explanations

    references to legal and judicial activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal proceedings and outcomes

    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
    cellaneous
    -0.66
     Currently
    -0.63
    izons
    -0.62
     perennial
    -0.62
    ichever
    -0.62
    asma
    -0.60
     Flavoring
    -0.59
    cius
    -0.58
     Emer
    -0.57
     lifespan
    -0.56
    POSITIVE LOGITS
     amounted
    1.56
     violated
    1.46
     violates
    1.44
     constituted
    1.38
     unfairly
    1.33
     infring
    1.29
     constitutes
    1.21
     harmed
    1.18
     interfered
    1.16
     lacked
    1.15
    Activations Density 0.357%

    No Known Activations