© 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 24576
    5. 8-RES_FS24576-JB
    6. 24168
    Prev
    Next
    INDEX
    Explanations

    references to fundraising activities and monetary amounts

    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
    269
    +0.12
    0.5%
    69
    +0.10
    0.5%
    317
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.12
    0.03
    444
    +0.10
    0.03
    149
    +0.10
    0.03
    Negative Logits
     Goodell
    -0.64
     Curry
    -0.63
    drivers
    -0.62
     fixme
    -0.60
    opol
    -0.60
     destroyer
    -0.60
    icion
    -0.59
     nib
    -0.59
     Spicer
    -0.59
    paio
    -0.58
    POSITIVE LOGITS
     crowdfunding
    1.11
     fundraising
    1.08
     donations
    1.01
     fundra
    0.99
     donation
    0.98
    funding
    0.94
    Fund
    0.92
    fund
    0.90
     funds
    0.90
     fundraiser
    0.89
    Activations Density 0.113%

    No Known Activations