© 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. 0-RES-JB
    11. 1181
    Prev
    Next
    INDEX
    Explanations

    words related to respect and disrespect

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with respectful and disrespectful behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     projections
    -0.72
    finder
    -0.71
    alth
    -0.70
    ipel
    -0.69
     Operation
    -0.69
    ylan
    -0.67
    Operation
    -0.66
    omal
    -0.64
    mac
    -0.64
    mega
    -0.64
    POSITIVE LOGITS
     respectful
    2.72
     disrespectful
    2.67
     polite
    2.27
     disrespect
    2.24
     respectfully
    2.09
     rude
    2.00
     politely
    1.70
     Respect
    1.59
     insulting
    1.57
     respecting
    1.50
    Activations Density 0.044%

    No Known Activations