© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1274
    Prev
    Next
    INDEX
    Explanations

    references to specific types of stores, items, and activities encountered in everyday life

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    481
    +0.27
    1.3%
    447
    +0.15
    0.7%
    575
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.27
    0.09
    288
    +0.15
    0.09
    435
    +0.12
    0.04
    Negative Logits
    xtap
    -0.70
    eatures
    -0.66
    Ĥİ
    -0.61
     Qiao
    -0.60
     Gleaming
    -0.60
     Cosponsors
    -0.59
    NetMessage
    -0.55
     griev
    -0.54
     fractions
    -0.54
    ahu
    -0.53
    POSITIVE LOGITS
     ASAP
    0.85
     handy
    0.83
     someday
    0.78
     anymore
    0.78
     protector
    0.74
     solution
    0.72
     ready
    0.72
    achable
    0.71
     capable
    0.71
     option
    0.70
    Activations Density 0.554%

    No Known Activations