© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17837
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of responsibility or duty

    oai_token-act-pair · gpt-3.5-turbo

    references to job responsibilities and duties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rumours
    -0.74
    eros
    -0.74
     rumors
    -0.71
    Lot
    -0.71
    acan
    -0.70
    ongh
    -0.70
    axy
    -0.68
    pot
    -0.67
    ston
    -0.66
    AX
    -0.66
    POSITIVE LOGITS
     obligation
    0.84
     responsibility
    0.71
     competence
    0.70
     duty
    0.68
     emancipation
    0.68
     restraint
    0.68
     constraint
    0.68
     task
    0.67
     theorem
    0.65
     respons
    0.65
    Activations Density 0.151%

    No Known Activations