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 24576
    5. 8-RES_FS24576-JB
    6. 991
    Prev
    Next
    INDEX
    Explanations

    medical emergencies and crimes reported in the news

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.11
    0.5%
    380
    +0.10
    0.4%
    150
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.11
    0.04
    114
    +0.10
    0.03
    150
    +0.09
    0.03
    Negative Logits
    soDeliveryDate
    -0.80
     à¨
    -0.77
    女
    -0.69
     hypocrisy
    -0.69
     DRAGON
    -0.68
     monopol
    -0.67
     quotas
    -0.66
     jealousy
    -0.66
    tags
    -0.66
     bandwagon
    -0.64
    POSITIVE LOGITS
     hospital
    1.33
    Doctors
    1.21
     paramedics
    1.14
     Hospital
    1.12
     hospitalized
    1.11
     injuries
    1.11
     Surgery
    1.10
     surgery
    1.10
     Doctors
    1.10
     medical
    1.10
    Activations Density 0.293%

    No Known Activations