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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 538
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, particularly full names including first, middle, and last names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    659
    +0.13
    0.6%
    430
    +0.12
    0.6%
    189
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.21
    232
    +0.12
    0.16
    430
    +0.12
    0.17
    Negative Logits
    taboola
    -0.98
    dayName
    -0.87
    pmwiki
    -0.83
    direction
    -0.83
    sites
    -0.82
    cffff
    -0.81
    leaders
    -0.77
    fecture
    -0.74
    Ħ¢
    -0.71
    paren
    -0.69
    POSITIVE LOGITS
     Roberts
    1.27
     Robinson
    1.26
     Hansen
    1.24
     Peters
    1.20
     Rodriguez
    1.20
     Martinez
    1.19
     Smith
    1.19
     Reed
    1.19
     Simmons
    1.18
     Hayes
    1.18
    Activations Density 1.755%

    No Known Activations