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. 1629
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological advancements and their impacts

    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
    307
    +0.09
    0.4%
    455
    +0.09
    0.4%
    583
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.09
    0.04
    89
    +0.09
    0.04
    700
    +0.09
    0.04
    Negative Logits
    anos
    -0.71
    bley
    -0.63
    inity
    -0.61
    mber
    -0.61
    kas
    -0.61
    mur
    -0.59
    atten
    -0.59
    rys
    -0.59
    mare
    -0.59
    arter
    -0.57
    POSITIVE LOGITS
    onse
    0.65
    Parameters
    0.63
    },"
    0.63
     known
    0.62
    ]);
    0.61
    Label
    0.61
     as
    0.61
    س
    0.60
     vers
    0.59
     suited
    0.57
    Activations Density 0.273%

    No Known Activations