© 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. 3-RES-JB
    11. 10667
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or regulatory applicability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -0.88
    ching
    -0.86
    cheon
    -0.83
    ochond
    -0.79
    nik
    -0.78
    buck
    -0.78
    airs
    -0.77
     Tycoon
    -0.77
    ting
    -0.75
    overe
    -0.75
    POSITIVE LOGITS
     applicable
    0.91
     APPLIC
    0.83
     reluct
    0.77
     applies
    0.77
    ãģĨ
    0.74
     apply
    0.70
    NESS
    0.69
     applied
    0.68
    alties
    0.67
     Authorities
    0.67
    Activations Density 0.013%

    No Known Activations