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. 1107
    Prev
    Next
    INDEX
    Explanations

    phrases related to emergency situations and responses

    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
    379
    +0.12
    0.6%
    606
    +0.10
    0.5%
    288
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.10
    132
    +0.10
    0.05
    418
    +0.10
    0.05
    Negative Logits
    nan
    -0.90
    atu
    -0.89
    artisan
    -0.88
    gemony
    -0.86
    hetti
    -0.83
    boa
    -0.82
    gling
    -0.81
    ophon
    -0.81
    orn
    -0.79
    bourg
    -0.79
    POSITIVE LOGITS
     responders
    1.07
     evacuation
    0.98
     emergency
    0.94
     evac
    0.93
     rescue
    0.93
    autions
    0.91
     evacuate
    0.91
     response
    0.88
     surge
    0.87
     liquidity
    0.82
    Activations Density 1.073%

    No Known Activations