© 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 3072
    9. 8-RES_FS3072-JB
    11. 235
    Prev
    Next
    INDEX
    Explanations

    phrases related to software installation and programming functions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    459
    +0.14
    0.6%
    326
    +0.13
    0.6%
    255
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    739
    +0.14
    0.06
    255
    +0.13
    0.09
    267
    +0.10
    0.09
    Negative Logits
    Amid
    -0.81
     Amid
    -0.78
     Rodham
    -0.78
    crime
    -0.74
    SHARE
    -0.72
    cellence
    -0.70
    nered
    -0.70
     passionately
    -0.69
    Dear
    -0.69
    justice
    -0.69
    POSITIVE LOGITS
     optional
    1.19
     exceptions
    1.08
     drawback
    1.07
     optionally
    1.05
     omit
    1.03
    optional
    1.02
     excludes
    1.00
     preferable
    0.99
     varies
    0.98
     vary
    0.98
    Activations Density 3.265%

    No Known Activations