© 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 24576
    9. 8-RES_FS24576-JB
    11. 9624
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    +0.24
    1.1%
    139
    +0.14
    0.7%
    561
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.24
    0.06
    561
    +0.14
    0.05
    765
    +0.10
    0.05
    Negative Logits
    ESA
    -0.65
    USE
    -0.64
    ãĥ¥
    -0.63
    erity
    -0.62
    irie
    -0.61
    ize
    -0.60
    ĵ
    -0.60
     Include
    -0.59
    ritical
    -0.59
    ELF
    -0.59
    POSITIVE LOGITS
     joins
    1.18
     remembers
    0.94
     pleaded
    0.91
     enjoys
    0.91
     joined
    0.90
     greets
    0.89
     earns
    0.89
     died
    0.88
     became
    0.87
     testified
    0.87
    Activations Density 0.168%

    No Known Activations