© 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 12288
    9. 8-RES_FS12288-JB
    11. 1841
    Prev
    Next
    INDEX
    Explanations

    specialized terminology and phrases related to military, politics, and law

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    226
    +0.10
    0.5%
    301
    +0.10
    0.4%
    465
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.06
    219
    +0.10
    0.04
    18
    +0.09
    0.04
    Negative Logits
     himself
    -0.91
     herself
    -0.86
    tein
    -0.75
     oneself
    -0.74
     Himself
    -0.70
    auri
    -0.68
     themselves
    -0.66
    imming
    -0.63
    nikov
    -0.63
     Stern
    -0.60
    POSITIVE LOGITS
     selves
    1.17
     ancestors
    0.98
     partners
    0.92
     asses
    0.92
     counterparts
    0.89
     brethren
    0.89
     ourselves
    0.84
     motto
    0.78
     overl
    0.76
     endeavors
    0.76
    Activations Density 0.310%

    No Known Activations