© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 12607
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of houses and related activities or locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    152
    +0.17
    0.8%
    531
    +0.10
    0.5%
    352
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.17
    0.04
    531
    +0.10
    0.03
    737
    +0.10
    0.03
    Negative Logits
    aneously
    -0.78
    ICAL
    -0.74
    aneous
    -0.70
     guiActiveUn
    -0.69
    uyomi
    -0.69
    ï¸ı
    -0.68
    DragonMagazine
    -0.66
    NetMessage
    -0.65
     CNS
    -0.65
    Grade
    -0.64
    POSITIVE LOGITS
    wife
    1.57
    wives
    1.54
    keeping
    1.30
    warming
    1.18
    keeper
    1.15
    mates
    1.13
    boat
    1.13
    boats
    1.10
    plant
    1.08
    husband
    1.01
    Activations Density 0.031%

    No Known Activations