© 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 24576
    9. 8-RES_FS24576-JB
    11. 1606
    Prev
    Next
    INDEX
    Explanations

    applications or forms related to official processes

    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
    276
    +0.12
    0.5%
    253
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.12
    0.02
    540
    +0.11
    0.02
    575
    +0.10
    0.02
    Negative Logits
    ottesville
    -0.66
    ilight
    -0.65
     msec
    -0.64
    ord
    -0.64
    ideshow
    -0.63
     Scourge
    -0.63
    ijk
    -0.63
     Beef
    -0.62
     Grip
    -0.62
     Assassins
    -0.61
    POSITIVE LOGITS
     deadline
    0.91
     submissions
    0.88
     submitted
    0.87
     paperwork
    0.86
    Applic
    0.86
     process
    0.85
     filed
    0.84
     fee
    0.84
     petitions
    0.83
     deadlines
    0.81
    Activations Density 0.040%

    No Known Activations