© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 37455
    Prev
    Next
    INDEX
    Explanations

    terms associated with food quality and dietary issues

    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
    480
    +0.62
    3.8%
    266
    +0.12
    0.7%
    351
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.62
    0.04
    480
    +0.12
    0.01
    174
    +0.06
    0.03
    Negative Logits
     Jub
    -0.49
    JC
    -0.48
     Crab
    -0.46
     Piper
    -0.46
     Isles
    -0.46
    ŃĶ
    -0.44
     Solitaire
    -0.44
     Summit
    -0.43
    church
    -0.43
    hunt
    -0.43
    POSITIVE LOGITS
    ating
    0.64
    ated
    0.64
    atically
    0.61
    ielding
    0.59
    aining
    0.59
    agging
    0.59
    ased
    0.58
    atching
    0.58
    antly
    0.57
    ationally
    0.57
    Activations Density 0.135%

    No Known Activations