© 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 49152
    9. 8-RES_FS49152-JB
    11. 37214
    Prev
    Next
    INDEX
    Explanations

    data about television series viewership and ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    606
    +0.10
    0.5%
    3
    +0.10
    0.4%
    159
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.10
    0.02
    196
    +0.10
    0.02
    260
    +0.09
    0.02
    Negative Logits
     sche
    -0.84
     PCB
    -0.74
     schematic
    -0.74
     biome
    -0.74
    ulic
    -0.71
     diagrams
    -0.71
     Malf
    -0.71
     symmetry
    -0.71
    obyl
    -0.70
     graphene
    -0.69
    POSITIVE LOGITS
     viewership
    1.17
     viewers
    1.08
     rating
    1.07
     Nielsen
    1.04
     Ratings
    1.04
    levision
    1.03
     ratings
    1.02
     theaters
    1.01
     Hulu
    1.00
     audience
    0.96
    Activations Density 0.076%

    No Known Activations