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. 1552
    Prev
    Next
    INDEX
    Explanations

    phrases related to donating money or other forms of support

    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
    322
    +0.10
    0.5%
    317
    +0.10
    0.5%
    707
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.08
    247
    +0.10
    0.04
    592
    +0.10
    0.04
    Negative Logits
     Mock
    -0.70
    iliar
    -0.67
    dar
    -0.66
    MAT
    -0.66
    corn
    -0.65
    jong
    -0.64
    arta
    -0.64
    downs
    -0.63
    nu
    -0.63
    down
    -0.63
    POSITIVE LOGITS
     generously
    1.10
     donation
    1.10
     donations
    1.10
     donated
    1.08
     donors
    0.96
     donating
    0.96
     Donation
    0.96
     donor
    0.93
     donate
    0.92
     fundra
    0.89
    Activations Density 0.889%

    No Known Activations