© 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. 1-RES-JB
    11. 23384
    Prev
    Next
    INDEX
    Explanations

    words related to ethical considerations

    oai_token-act-pair · gpt-3.5-turbo

    references to ethical standards and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lling
    -0.81
    hof
    -0.80
    jong
    -0.78
    early
    -0.77
    down
    -0.75
    eding
    -0.75
    coat
    -0.75
    peak
    -0.73
    upt
    -0.72
     Pinterest
    -0.72
    POSITIVE LOGITS
    ethical
    1.30
     ethical
    1.24
     ethics
    1.06
    onomic
    1.00
     dile
    0.96
     volunt
    0.85
     Ethics
    0.82
     ethic
    0.81
     considerations
    0.79
     breaches
    0.79
    Activations Density 0.010%

    No Known Activations