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. 1179
    Prev
    Next
    INDEX
    Explanations

    social media handles and user mentions

    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
    •URL Group
    •Twitter

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    145
    +0.14
    0.7%
    238
    +0.09
    0.4%
    267
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.14
    0.04
    577
    +0.09
    0.04
    488
    +0.09
    0.04
    Negative Logits
     scrut
    -0.74
     shorth
    -0.67
     carbohyd
    -0.65
     beginners
    -0.63
     sidx
    -0.60
     deduct
    -0.59
     carts
    -0.59
     mathemat
    -0.58
     complement
    -0.58
     stip
    -0.58
    POSITIVE LOGITS
    Jr
    0.88
     CrossRef
    0.86
    ._
    0.82
    qq
    0.81
    dc
    0.80
     pic
    0.79
    /?
    0.78
    Uk
    0.78
    q
    0.76
    jj
    0.75
    Activations Density 0.041%

    No Known Activations