© 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. 4-RES-JB
    11. 10150
    Prev
    Next
    INDEX
    Explanations

    mentions of non-compliance and violations of regulations or laws

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to legal compliance

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

    No Comments

    Negative Logits
    orah
    -0.85
    ndra
    -0.74
    hler
    -0.70
    ulz
    -0.69
    ouf
    -0.68
    bably
    -0.65
    chief
    -0.65
    mAh
    -0.64
    ju
    -0.64
    edin
    -0.64
    POSITIVE LOGITS
     laws
    0.70
     stringent
    0.69
     orders
    0.69
     obligations
    0.69
     directives
    0.69
     norms
    0.69
     instructions
    0.68
     provisions
    0.67
     regulations
    0.67
     their
    0.66
    Activations Density 0.073%

    No Known Activations