© 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. 41467
    Prev
    Next
    INDEX
    Explanations

    terms related to ripple effects and systemic impacts

    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
    195
    +0.12
    0.5%
    442
    +0.12
    0.5%
    578
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    195
    +0.12
    0.01
    271
    +0.10
    0.01
    Negative Logits
    unte
    -0.85
    phis
    -0.80
    ramer
    -0.80
    uni
    -0.74
    ctic
    -0.74
    rar
    -0.74
    ation
    -0.72
    atel
    -0.70
    seless
    -0.70
    glers
    -0.70
    POSITIVE LOGITS
     ripple
    1.23
     effect
    1.11
     effects
    0.99
     Effect
    0.92
    Effects
    0.90
     Effects
    0.88
    effects
    0.85
    Effect
    0.82
     downstream
    0.80
     sclerosis
    0.79
    Activations Density 0.023%

    No Known Activations