© 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. 22160
    Prev
    Next
    INDEX
    Explanations

    references to market conditions or market analysis

    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
    496
    +0.14
    0.7%
    160
    +0.12
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.14
    0.03
    160
    +0.12
    0.03
    681
    +0.12
    0.03
    Negative Logits
    tein
    -0.71
     Drac
    -0.69
     Lod
    -0.67
     Lak
    -0.65
     Protective
    -0.64
     tatt
    -0.63
    ignt
    -0.62
     Banner
    -0.60
     Fan
    -0.60
    utan
    -0.60
    POSITIVE LOGITS
    places
    1.56
    hare
    1.27
    eers
    1.22
    eer
    0.94
    ability
    0.88
    place
    0.83
     share
    0.82
    ele
    0.81
    eering
    0.80
     niche
    0.79
    Activations Density 0.035%

    No Known Activations