© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    words related to romantic relationships and dating

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    247
    +0.11
    0.5%
    186
    +0.11
    0.5%
    340
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.11
    0.04
    575
    +0.11
    0.04
    288
    +0.10
    0.05
    Negative Logits
    Downloadha
    -0.83
    Reviewer
    -0.78
    £ı
    -0.77
    osta
    -0.76
    é¾
    -0.75
    steen
    -0.73
     recoil
    -0.73
    ulic
    -0.72
    TPPStreamerBot
    -0.71
     Printed
    -0.70
    POSITIVE LOGITS
     monog
    0.97
     girlfriend
    0.94
     partner
    0.94
     girlfriends
    0.93
     couples
    0.92
     boyfriend
    0.91
    girlfriend
    0.91
     lia
    0.85
     rom
    0.84
     romance
    0.83
    Activations Density 0.237%

    No Known Activations