© 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. 18660
    Prev
    Next
    INDEX
    Explanations

    information related to scientific and technical 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
    762
    +0.14
    0.6%
    481
    +0.12
    0.5%
    220
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.14
    0.05
    594
    +0.12
    0.04
    647
    +0.11
    0.04
    Negative Logits
    daq
    -0.77
    soDeliveryDate
    -0.76
    luaj
    -0.74
    Champ
    -0.73
    BuyableInstoreAndOnline
    -0.71
    EStream
    -0.69
     Spectre
    -0.68
    PLA
    -0.68
    æµ
    -0.67
    MSN
    -0.67
    POSITIVE LOGITS
     combining
    0.89
    akens
    0.74
     loosely
    0.73
     particles
    0.73
     whereby
    0.72
     alternating
    0.72
    ensation
    0.72
     surg
    0.72
     enclosed
    0.71
     combines
    0.70
    Activations Density 0.783%

    No Known Activations