Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 494
    Prev
    Next
    INDEX
    Explanations

    phrases related to the criminal justice system

    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
    447
    +0.12
    0.5%
    368
    +0.11
    0.5%
    455
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.05
    724
    +0.11
    0.05
    325
    +0.11
    0.04
    Negative Logits
    tein
    -0.89
    £ı
    -0.72
    CHAT
    -0.69
    sbm
    -0.69
    ocular
    -0.68
    Fil
    -0.68
    20439
    -0.68
    pload
    -0.68
    brew
    -0.66
    amiya
    -0.66
    POSITIVE LOGITS
     continuum
    0.91
     reform
    0.86
     crisis
    0.84
     itself
    0.83
     sclerosis
    0.82
     deregulation
    0.82
     reforms
    0.81
     bureaucracy
    0.81
     Accountability
    0.80
     parity
    0.79
    Activations Density 0.176%

    No Known Activations