© 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 49152
    9. 8-RES_FS49152-JB
    11. 25816
    Prev
    Next
    INDEX
    Explanations

    the second person pronoun "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.14
    0.6%
    383
    +0.12
    0.5%
    49
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.14
    0.04
    354
    +0.12
    0.04
    383
    +0.10
    0.03
    Negative Logits
    ipal
    -0.81
    imon
    -0.79
    entimes
    -0.72
    BuyableInstoreAndOnline
    -0.72
     Crown
    -0.63
    grave
    -0.63
     Laurent
    -0.62
    upe
    -0.62
    ¿½
    -0.62
    ãĥ³ãĤ¸
    -0.59
    POSITIVE LOGITS
    're
    1.54
    've
    1.24
    'll
    1.23
    tub
    1.21
     guys
    1.21
    'd
    1.13
    RS
    1.07
     wanna
    0.96
     guessed
    0.90
     want
    0.87
    Activations Density 0.063%

    No Known Activations