© 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. 10-RES-JB
    11. 10165
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing love or admiration for someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of letters and initials, particularly those that might signify names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 10 - love

    No Comments

    Negative Logits
     fragmentation
    -0.70
     Dickinson
    -0.62
     timing
    -0.62
    ativity
    -0.61
    coni
    -0.60
     friction
    -0.60
     sandbox
    -0.60
    poly
    -0.60
    phony
    -0.59
    aic
    -0.59
    POSITIVE LOGITS
    ought
    1.14
    ained
    1.13
    owed
    1.03
    stood
    1.00
    OULD
    1.00
    ounced
    0.99
    aughed
    0.99
    overed
    0.98
    icipated
    0.98
    poses
    0.97
    Activations Density 0.187%

    No Known Activations