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. 21355
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "as a"

    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
    36
    +0.23
    1.1%
    393
    +0.17
    0.8%
    362
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.23
    0.14
    512
    +0.17
    0.07
    250
    +0.12
    0.05
    Negative Logits
    Edit
    -0.96
    achu
    -0.92
    items
    -0.80
    mins
    -0.80
    edit
    -0.77
    Arizona
    -0.75
    eston
    -0.75
    ioch
    -0.75
    Images
    -0.74
    ographs
    -0.74
    POSITIVE LOGITS
     nuisance
    1.19
    versive
    1.08
     mere
    1.06
     distraction
    1.06
     coincidence
    1.06
     threat
    1.04
     continuation
    1.02
     necessity
    1.02
     legitimate
    1.01
     hoax
    1.00
    Activations Density 0.255%

    No Known Activations