© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 1029
    Prev
    Next
    INDEX
    Explanations

    legal and law enforcement terms and procedures

    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
    393
    +0.21
    1.1%
    570
    +0.13
    0.7%
    208
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.26
    575
    +0.13
    0.21
    570
    +0.11
    0.03
    Negative Logits
    osaurs
    -0.65
    ãĥ£
    -0.65
    natureconservancy
    -0.61
    20439
    -0.60
    ãĥķãĤ©
    -0.60
    ãĤ£
    -0.59
    ãĤµ
    -0.58
    ertain
    -0.58
    Flickr
    -0.57
    arious
    -0.57
    POSITIVE LOGITS
    rique
    0.73
    eers
    0.69
     rul
    0.69
     equivalents
    0.62
     Azerb
    0.58
     skelet
    0.57
     LM
    0.56
    alion
    0.56
     secondly
    0.56
     Citadel
    0.56
    Activations Density 8.729%

    No Known Activations