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. 26224
    Prev
    Next
    INDEX
    Explanations

    terms related to irrelevance and instability

    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
    124
    +0.10
    0.5%
    184
    +0.10
    0.5%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.01
    165
    +0.10
    0.01
    702
    +0.10
    0.01
    Negative Logits
    ulhu
    -0.69
    emouth
    -0.66
    arnaev
    -0.64
    hler
    -0.63
    creen
    -0.63
    ahi
    -0.61
    yip
    -0.60
     Lumpur
    -0.58
    ifle
    -0.58
    EStream
    -0.57
    POSITIVE LOGITS
    itely
    0.80
    ivably
    0.77
    ¿
    0.70
    ably
    0.69
    inary
    0.69
    nces
    0.68
    lihood
    0.67
    ministic
    0.67
    forced
    0.66
    ception
    0.66
    Activations Density 0.011%

    No Known Activations