© 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. 15818
    Prev
    Next
    INDEX
    Explanations

    phrases related to different religions and their impact on society

    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
    481
    +0.21
    1.0%
    642
    +0.12
    0.5%
    401
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.21
    0.04
    7
    +0.12
    0.03
    102
    +0.11
    0.05
    Negative Logits
     Tracker
    -0.82
    oops
    -0.82
    ventory
    -0.81
    timeout
    -0.79
    Timeout
    -0.78
     deadlines
    -0.76
    bucks
    -0.75
     Delivery
    -0.74
    Async
    -0.74
    pletion
    -0.74
    POSITIVE LOGITS
     ideology
    1.10
     Christianity
    1.08
     Judaism
    1.08
     religion
    1.07
     theology
    1.07
     anarchism
    1.04
     traditions
    1.04
     adherents
    1.03
     beliefs
    1.02
     Catholicism
    1.02
    Activations Density 0.528%

    No Known Activations