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 3072
    5. 8-RES_FS3072-JB
    6. 2267
    Prev
    Next
    INDEX
    Explanations

    information related to specific events or advertisements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    +0.67
    4.0%
    266
    +0.15
    0.9%
    447
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.67
    0.05
    266
    +0.15
    0.25
    367
    +0.10
    0.15
    Negative Logits
     anyway
    -0.57
     legitimately
    -0.55
     inherently
    -0.55
     lawy
    -0.54
     necessarily
    -0.53
     policies
    -0.53
     fundamentally
    -0.53
     broadly
    -0.52
     increasingly
    -0.52
     objectively
    -0.52
    POSITIVE LOGITS
    Joined
    0.57
     Variant
    0.57
     Optical
    0.54
    itone
    0.53
     Daughter
    0.51
     Nanto
    0.50
     Seas
    0.49
     turret
    0.48
    çͰ
    0.48
     Mk
    0.48
    Activations Density 7.355%

    No Known Activations