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 49152
    5. 8-RES_FS49152-JB
    6. 46179
    Prev
    Next
    INDEX
    Explanations

    references to young people and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    157
    +0.11
    0.5%
    660
    +0.10
    0.5%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    660
    +0.11
    0.03
    325
    +0.10
    0.03
    762
    +0.09
    0.03
    Negative Logits
    orius
    -0.89
    âķIJ
    -0.87
    pmwiki
    -0.84
    ãĥ¢
    -0.83
    ãĥĥ
    -0.83
    ãĥ¯ãĥ³
    -0.81
     Cosponsors
    -0.77
    saf
    -0.75
    Accessory
    -0.75
    ãĥĥãĥĪ
    -0.75
    POSITIVE LOGITS
     graduating
    0.95
     ages
    0.88
     aged
    0.88
     aspiring
    0.88
     graduates
    0.86
     enroll
    0.85
     immersed
    0.85
     aspir
    0.82
     enrolled
    0.81
     disillusion
    0.80
    Activations Density 0.097%

    No Known Activations