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. 23316
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-4o-miniTriggered 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
    480
    +0.47
    2.4%
    659
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.47
    0.11
    232
    +0.10
    0.08
    145
    +0.10
    0.05
    Negative Logits
     manipulating
    -0.69
    tumblr
    -0.67
     partying
    -0.65
     discriminated
    -0.63
     handshake
    -0.58
     lockout
    -0.58
     womb
    -0.57
     originated
    -0.57
     proved
    -0.56
     overshadowed
    -0.56
    POSITIVE LOGITS
    anton
    0.81
    ijn
    0.80
    yna
    0.78
    je
    0.77
    anan
    0.75
    hiro
    0.74
    elli
    0.73
    sten
    0.72
    arie
    0.72
    oj
    0.72
    Activations Density 0.365%

    No Known Activations