© 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 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. 12208
    Prev
    Next
    INDEX
    Explanations

    company or business-related terms

    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
    316
    +0.12
    0.6%
    471
    +0.10
    0.5%
    36
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.12
    0.01
    316
    +0.10
    0.01
    637
    +0.10
    0.01
    Negative Logits
     explan
    -0.77
    ancial
    -0.74
    arium
    -0.73
    omore
    -0.63
    perse
    -0.63
    ician
    -0.62
    izations
    -0.61
    ciating
    -0.61
    behind
    -0.61
     Gors
    -0.61
    POSITIVE LOGITS
    RIC
    1.07
    stract
    1.03
    STR
    0.98
    OUT
    0.96
    RAM
    0.96
    ORN
    0.92
    JECT
    0.88
    UL
    0.87
    yrinth
    0.86
    raham
    0.86
    Activations Density 0.010%

    No Known Activations