© 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 24576
    9. 8-RES_FS24576-JB
    11. 1360
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or comparison of qualities

    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
    565
    +0.12
    0.5%
    383
    +0.11
    0.5%
    162
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    565
    +0.12
    0.02
    441
    +0.11
    0.02
    716
    +0.11
    0.02
    Negative Logits
     Canaver
    -0.77
     Coff
    -0.71
    glers
    -0.70
    ocene
    -0.69
    liest
    -0.68
    ASE
    -0.66
     Benson
    -0.65
     Reborn
    -0.65
    wrap
    -0.65
     Liang
    -0.64
    POSITIVE LOGITS
     situated
    0.97
     spaced
    0.96
     weighted
    0.93
     sized
    0.89
     applicable
    0.85
    inguishable
    0.82
    imilar
    0.81
     adept
    0.81
     stringent
    0.79
     pronounced
    0.78
    Activations Density 0.016%

    No Known Activations