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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3866
    Prev
    Next
    INDEX
    Explanations

    expressions related to hierarchical relationships and interactions between individuals, including acts of obedience, respect, subordination, admiration, and authority

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to social dynamics and responsibilities, particularly those highlighting respect, submission, and societal shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corrid
    -0.71
     orally
    -0.69
     commentators
    -0.67
     indications
    -0.67
     annot
    -0.66
     datasets
    -0.66
     earners
    -0.64
     explan
    -0.64
     descendants
    -0.63
     groceries
    -0.62
    POSITIVE LOGITS
    ility
    1.68
    leness
    1.63
    itiveness
    1.57
    eness
    1.56
    iness
    1.50
    iability
    1.49
    idity
    1.49
    ability
    1.48
    iveness
    1.47
    iosity
    1.45
    Activations Density 0.448%

    No Known Activations