© 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. 2258
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules and consequences

    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
    230
    +0.11
    0.5%
    447
    +0.11
    0.5%
    698
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.08
    698
    +0.11
    0.06
    762
    +0.09
    0.08
    Negative Logits
     Hels
    -0.59
     newcom
    -0.55
    çīĪ
    -0.53
     Zy
    -0.52
     looph
    -0.52
     showc
    -0.52
    bestos
    -0.51
     Ath
    -0.51
    chieve
    -0.51
     Atkins
    -0.51
    POSITIVE LOGITS
     anymore
    0.82
     then
    0.82
     beforehand
    0.80
     there
    0.80
     THEN
    0.80
     they
    0.76
    then
    0.76
    ,
    0.74
    ?,
    0.74
     thats
    0.72
    Activations Density 0.676%

    No Known Activations