© 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. 1-RES-JB
    11. 22505
    Prev
    Next
    INDEX
    Explanations

    words related to expressing positive emotions, particularly affection

    oai_token-act-pair · gpt-3.5-turbo

    expressions of love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.81
    ulhu
    -0.77
    ÄŁ
    -0.75
     Worlds
    -0.71
    zh
    -0.68
     Pharma
    -0.66
     Klu
    -0.66
     Roth
    -0.63
    reens
    -0.63
    Ber
    -0.62
    POSITIVE LOGITS
     affection
    1.31
    ately
    1.17
    naire
    1.09
    uously
    0.96
    uous
    0.89
    ate
    0.88
    atile
    0.88
     destro
    0.85
    ually
    0.84
    acy
    0.84
    Activations Density 0.011%

    No Known Activations