© 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. 3-RES-JB
    11. 1750
    Prev
    Next
    INDEX
    Explanations

    the word "mutual" and related phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mutual" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regon
    -0.88
    OPLE
    -0.76
    agate
    -0.76
     Horizon
    -0.72
    Blog
    -0.72
     Dare
    -0.71
    tto
    -0.70
    den
    -0.69
    ̶
    -0.69
    byss
    -0.67
    POSITIVE LOGITS
     mutual
    1.05
     acquaintance
    0.90
     agreement
    0.87
     parting
    0.84
     reciproc
    0.83
     acquaintances
    0.79
     arrangement
    0.79
     reciprocal
    0.79
     masturbation
    0.78
     consent
    0.77
    Activations Density 0.009%

    No Known Activations