Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1479
    Prev
    Next
    INDEX
    Explanations

    references to events happening at late times of day or year

    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
    18
    +0.10
    0.5%
    746
    +0.10
    0.5%
    319
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.10
    0.04
    296
    +0.10
    0.04
    746
    +0.10
    0.03
    Negative Logits
    edIn
    -0.81
     Pwr
    -0.79
    ikk
    -0.76
    ebook
    -0.70
    adr
    -0.68
    ili
    -0.67
    roma
    -0.67
    ophers
    -0.67
    éĹĺ
    -0.67
    erie
    -0.67
    POSITIVE LOGITS
     afternoon
    1.16
     evening
    0.91
     twenties
    0.90
     nights
    0.90
     morning
    0.88
     adolescence
    0.87
     night
    0.86
    -'
    0.85
     evenings
    0.83
     mornings
    0.82
    Activations Density 0.252%

    No Known Activations