© 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. 2-RES-JB
    11. 9454
    Prev
    Next
    INDEX
    Explanations

    terms related to courtship and politeness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to courting or attempting to win favor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.76
    hyde
    -0.71
    ĸļ
    -0.68
    acea
    -0.68
    galitarian
    -0.67
     Ghana
    -0.66
    adder
    -0.65
     Redemption
    -0.65
    profit
    -0.64
     buckle
    -0.62
    POSITIVE LOGITS
     cour
    1.26
    cour
    0.89
    zens
    0.84
    issance
    0.83
    iour
    0.82
    tesy
    0.82
    ries
    0.82
    berus
    0.79
    sed
    0.78
    itably
    0.78
    Activations Density 0.006%

    No Known Activations