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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 21574
    Prev
    Next
    INDEX
    Explanations

    terms related to workplace issues and management practices that impact employee performance

    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
    481
    +0.13
    0.6%
    288
    +0.12
    0.5%
    391
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.03
    391
    +0.12
    0.02
    575
    +0.10
    0.02
    Negative Logits
    quet
    -0.85
    ovich
    -0.84
    iasis
    -0.81
    istant
    -0.81
    atra
    -0.79
    ibo
    -0.78
    ema
    -0.77
    ional
    -0.77
    eta
    -0.76
    olini
    -0.76
    POSITIVE LOGITS
    halla
    0.85
     Advantage
    0.76
     antics
    0.73
     divid
    0.69
     environment
    0.68
     chemistry
    0.67
     erg
    0.66
     readiness
    0.66
     bargaining
    0.65
     environments
    0.64
    Activations Density 0.054%

    No Known Activations