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. 1570
    Prev
    Next
    INDEX
    Explanations

    time-related information and event details

    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
    314
    +0.13
    0.6%
    132
    +0.11
    0.5%
    123
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.13
    0.10
    260
    +0.11
    0.10
    693
    +0.11
    0.09
    Negative Logits
    ĸļ
    -0.78
    atis
    -0.74
    amaru
    -0.72
    isoft
    -0.71
    rolet
    -0.66
    orem
    -0.66
    uras
    -0.64
    ovie
    -0.64
    querade
    -0.63
    ramid
    -0.62
    POSITIVE LOGITS
    00
    1.43
    th
    1.11
    rd
    1.05
    50
    1.04
    nm
    1.01
    %-
    0.96
    nd
    0.94
    60
    0.93
    mph
    0.91
    80
    0.89
    Activations Density 0.534%

    No Known Activations