© 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. 4-RES-JB
    11. 7249
    Prev
    Next
    INDEX
    Explanations

    words related to affection and love

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 4 - love

    No Comments

    Negative Logits
    Downloadha
    -0.78
    inates
    -0.75
    */(
    -0.74
    ublic
    -0.70
    ople
    -0.68
    OUGH
    -0.67
    icals
    -0.66
     Thieves
    -0.66
    Files
    -0.66
    urdue
    -0.66
    POSITIVE LOGITS
    tons
    0.83
    glers
    0.74
    cipled
    0.74
    minded
    0.73
     kindness
    0.73
     Heavenly
    0.72
     beings
    0.70
     minded
    0.69
    kind
    0.69
    ton
    0.68
    Activations Density 0.035%

    No Known Activations