© 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. 1112
    Prev
    Next
    INDEX
    Explanations

    texts referring to comparisons or similarities

    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
    373
    +0.17
    0.8%
    573
    +0.11
    0.5%
    483
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    229
    +0.17
    0.06
    172
    +0.11
    0.06
    647
    +0.10
    0.06
    Negative Logits
    ennes
    -0.78
    Published
    -0.77
    inas
    -0.76
    iets
    -0.71
    hiba
    -0.70
    inion
    -0.68
    ione
    -0.67
    overy
    -0.66
    anthrop
    -0.65
    ilic
    -0.65
    POSITIVE LOGITS
    lihood
    2.04
    liest
    1.45
    lier
    1.37
    minded
    1.14
     minded
    1.12
    liness
    1.07
     clock
    0.83
     ours
    0.82
     wildfire
    0.80
    ability
    0.78
    Activations Density 0.973%

    No Known Activations