© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22697
    Prev
    Next
    INDEX
    Explanations

    the word "It" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.15
    0.7%
    757
    +0.11
    0.5%
    139
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.15
    0.07
    571
    +0.11
    0.06
    655
    +0.11
    0.06
    Negative Logits
    dding
    -0.64
    hips
    -0.60
     Saying
    -0.60
    Ĥ¬
    -0.60
     Siri
    -0.59
     dstg
    -0.59
     stuffing
    -0.59
    Knowing
    -0.59
     Rebellion
    -0.57
    Wilson
    -0.56
    POSITIVE LOGITS
     consists
    1.29
     consisted
    1.25
     comprises
    1.18
     originated
    1.10
     contains
    1.07
     represents
    1.05
     involves
    1.04
     revolves
    1.01
    unes
    0.99
     arose
    0.99
    Activations Density 0.205%

    No Known Activations