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 6144
    5. 8-RES_FS6144-JB
    6. 4472
    Prev
    Next
    INDEX
    Explanations

    verbs related to recording or documenting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    380
    +0.12
    0.5%
    570
    +0.12
    0.5%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.12
    0.05
    541
    +0.12
    0.04
    529
    +0.12
    0.04
    Negative Logits
    bags
    -0.69
    cup
    -0.68
    ggles
    -0.66
    cloth
    -0.66
    enta
    -0.66
     assum
    -0.65
    kick
    -0.64
     drawer
    -0.64
    adin
    -0.63
    prep
    -0.62
    POSITIVE LOGITS
     footage
    0.86
     recordings
    0.81
     firsthand
    0.77
     audio
    0.73
     Aerial
    0.71
     conversations
    0.71
     LIVE
    0.70
    oufl
    0.69
     Peaks
    0.68
    recorded
    0.67
    Activations Density 0.384%

    No Known Activations