Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1493
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration or partnership

    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
    679
    +0.15
    0.7%
    1
    +0.10
    0.5%
    746
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.15
    0.04
    468
    +0.10
    0.04
    101
    +0.10
    0.05
    Negative Logits
    intendent
    -0.74
    framework
    -0.64
    mercial
    -0.63
    bane
    -0.63
     equival
    -0.62
    particularly
    -0.62
    astrous
    -0.62
     tiss
    -0.62
    effic
    -0.61
    andi
    -0.61
    POSITIVE LOGITS
     forces
    1.05
     ranks
    0.88
     Forces
    0.82
    TAIN
    0.79
    ATURES
    0.76
    OOL
    0.76
    lehem
    0.72
     hands
    0.70
    fleet
    0.70
     together
    0.69
    Activations Density 0.496%

    No Known Activations