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. 8416
    Prev
    Next
    INDEX
    Explanations

    phrases related to skepticism or critical questioning

    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
    55
    +0.12
    0.5%
    513
    +0.11
    0.5%
    553
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.12
    0.02
    513
    +0.11
    0.01
    553
    +0.10
    0.01
    Negative Logits
    rup
    -0.68
    elve
    -0.65
    nce
    -0.63
    odan
    -0.63
    rament
    -0.62
     centerpiece
    -0.61
    rique
    -0.60
    oute
    -0.59
    imble
    -0.57
    ggles
    -0.57
    POSITIVE LOGITS
     anyways
    0.99
     anyway
    0.90
    ãģĨ
    0.82
    entimes
    0.80
    hin
    0.78
     :-)
    0.76
     ;)
    0.75
    ãħĭ
    0.75
     reluct
    0.74
    â̦)
    0.74
    Activations Density 0.024%

    No Known Activations