© 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. 22593
    Prev
    Next
    INDEX
    Explanations

    different clauses related to legal terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of clauses or phrases related to legal or regulatory language

    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
    mire
    -0.75
    Enlarge
    -0.70
    joy
    -0.66
    onica
    -0.66
    nov
    -0.64
    ãĥŁ
    -0.62
    leon
    -0.61
    worldly
    -0.61
    veland
    -0.60
    ursday
    -0.59
    POSITIVE LOGITS
     regardless
    1.29
     irrespective
    1.27
     unless
    1.19
     including
    1.18
     punishable
    1.07
     INCLUD
    1.03
     pursuant
    1.03
     namely
    1.02
     notwithstanding
    1.01
     except
    1.00
    Activations Density 0.272%

    No Known Activations