© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19489
    Prev
    Next
    INDEX
    Explanations

    details related to television show seasons and premieres

    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
    159
    +0.11
    0.5%
    3
    +0.10
    0.5%
    151
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.11
    0.02
    162
    +0.10
    0.02
    434
    +0.09
    0.02
    Negative Logits
     biome
    -0.77
     Flask
    -0.76
     Malf
    -0.75
     Lotus
    -0.71
    ndra
    -0.71
    ulic
    -0.70
     sche
    -0.69
    orius
    -0.68
     Fabric
    -0.67
    lain
    -0.67
    POSITIVE LOGITS
    levision
    1.23
     viewership
    1.19
     Hulu
    1.06
     viewers
    1.06
     Nielsen
    1.05
    TV
    1.03
     theaters
    1.00
     ratings
    1.00
     telev
    0.97
     Ratings
    0.96
    Activations Density 0.117%

    No Known Activations