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 6144
    5. 8-RES_FS6144-JB
    6. 2743
    Prev
    Next
    INDEX
    Explanations

    references to various issues in the political and social spheres, ranging from historical figures to current events like security policies and international relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    408
    +0.12
    0.5%
    443
    +0.12
    0.5%
    608
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.12
    0.10
    344
    +0.12
    0.09
    608
    +0.11
    0.10
    Negative Logits
    hooting
    -0.74
    FIG
    -0.69
    yond
    -0.69
     Posts
    -0.68
    Os
    -0.67
    inet
    -0.65
    bis
    -0.65
    interstitial
    -0.63
    ILL
    -0.62
    ī
    -0.62
    POSITIVE LOGITS
     knack
    1.24
     chance
    1.17
     tendency
    1.02
     vested
    0.97
     penchant
    0.97
     reputation
    0.94
     opportunity
    0.89
     recourse
    0.89
     clue
    0.88
     affinity
    0.86
    Activations Density 0.683%

    No Known Activations