© 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. 26651
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opportunities and entitlements

    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
    756
    +0.12
    0.5%
    39
    +0.10
    0.5%
    419
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.03
    512
    +0.10
    0.03
    13
    +0.10
    0.03
    Negative Logits
    viol
    -0.60
     sinners
    -0.59
     murders
    -0.59
     incompetence
    -0.59
     delet
    -0.59
     robberies
    -0.59
    Mo
    -0.59
    strip
    -0.58
     Strauss
    -0.58
     suicides
    -0.57
    POSITIVE LOGITS
     opportunity
    1.08
     chance
    1.05
     glimpse
    1.01
     choice
    0.94
     firsthand
    0.92
     access
    0.92
     recourse
    0.85
    amiliar
    0.80
     insight
    0.80
     assurance
    0.79
    Activations Density 0.103%

    No Known Activations