© 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 3072
    9. 8-RES_FS3072-JB
    11. 234
    Prev
    Next
    INDEX
    Explanations

    information related to American football, coaching staff, and team history

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    373
    +0.50
    5.0%
    447
    +0.34
    3.4%
    756
    +0.12
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.50
    -0.19
    756
    +0.34
    -0.11
    459
    +0.12
    0.09
    Negative Logits
    etheless
    -0.32
     sqor
    -0.26
    Commerce
    -0.26
    displayText
    -0.24
    stellar
    -0.24
    ieu
    -0.23
     uniformly
    -0.23
    cedented
    -0.23
    tails
    -0.23
    neau
    -0.22
    POSITIVE LOGITS
     Cele
    0.27
     Kardash
    0.24
     Mew
    0.23
     electrom
    0.22
     Playboy
    0.21
    XXX
    0.21
     Gloria
    0.21
     Vaugh
    0.21
    outube
    0.21
     Oprah
    0.20
    Activations Density 10.654%

    No Known Activations