© 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. 8-RES-JB
    11. 9837
    Prev
    Next
    INDEX
    Explanations

    expressions of love

    oai_token-act-pair · gpt-3.5-turbo

    expressions of love or affection towards various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 8 - love
    •layer 8 - love

    No Comments

    Negative Logits
    aunder
    -0.83
    wcs
    -0.74
    ratulations
    -0.73
    ocument
    -0.71
    inel
    -0.70
    onew
    -0.70
    rief
    -0.69
    hof
    -0.69
    door
    -0.69
    DragonMagazine
    -0.68
    POSITIVE LOGITS
     tink
    0.90
     motorcycles
    0.80
     hobbies
    0.79
     automobiles
    0.78
     sweets
    0.76
     melody
    0.73
     music
    0.70
     antique
    0.70
    ffee
    0.69
     poetry
    0.68
    Activations Density 0.177%

    No Known Activations