© 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 EvalsExportsinterp-engineNEWAPI 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. 14642
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or lack of clarity

    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
    430
    +0.12
    0.5%
    218
    +0.10
    0.5%
    151
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.12
    0.03
    490
    +0.10
    0.03
    151
    +0.10
    0.03
    Negative Logits
     Emin
    -0.79
     Enhancement
    -0.70
     Metallic
    -0.67
    IDA
    -0.67
     Gore
    -0.66
    isma
    -0.64
    çļ
    -0.63
     TAMADRA
    -0.61
     Mechanical
    -0.59
     Might
    -0.58
    POSITIVE LOGITS
     anymore
    1.05
     nor
    0.96
    acea
    0.83
     yet
    0.76
    atican
    0.74
    proof
    0.71
     necessarily
    0.71
    achable
    0.71
    yet
    0.70
     accurate
    0.69
    Activations Density 0.087%

    No Known Activations