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 1536
    5. 8-RES_FS1536-JB
    6. 1191
    Prev
    Next
    INDEX
    Explanations

    monetary values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.18
    0.8%
    578
    +0.11
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.18
    0.06
    149
    +0.11
    0.06
    604
    +0.10
    0.06
    Negative Logits
     exerc
    -0.76
     Tall
    -0.75
     Sed
    -0.72
     Pend
    -0.72
     Reborn
    -0.71
     Gors
    -0.71
     Tid
    -0.69
     Vid
    -0.69
     Redd
    -0.66
     Freed
    -0.66
    POSITIVE LOGITS
    $$
    1.25
    100
    1.24
    250
    1.22
    500
    1.22
    150
    1.21
    300
    1.21
    200
    1.20
    400
    1.18
    1
    1.16
    350
    1.15
    Activations Density 0.508%

    No Known Activations