© 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. 6-RES-JB
    11. 19758
    Prev
    Next
    INDEX
    Explanations

    phrases related to mutual agreements or relationships

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mutual" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.83
    byss
    -0.82
    regon
    -0.80
    OPLE
    -0.76
    dq
    -0.74
     Flags
    -0.73
    agate
    -0.72
    kins
    -0.71
     Dare
    -0.71
    mb
    -0.70
    POSITIVE LOGITS
     agreement
    1.00
     mutual
    0.88
     reciproc
    0.85
     acquaintance
    0.85
     admiration
    0.83
     masturbation
    0.80
     incomp
    0.80
     acquaintances
    0.79
     correspondence
    0.77
     consent
    0.76
    Activations Density 0.014%

    No Known Activations