© 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. 19504
    Prev
    Next
    INDEX
    Explanations

    personal pronouns standing alone

    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
    566
    +0.14
    0.7%
    502
    +0.12
    0.6%
    336
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.14
    0.03
    566
    +0.12
    0.02
    93
    +0.09
    0.02
    Negative Logits
    theless
    -0.78
    rules
    -0.69
    rooms
    -0.67
    imentary
    -0.66
    taboola
    -0.62
     cov
    -0.61
     combustion
    -0.59
    ded
    -0.59
    ynamic
    -0.58
    spawn
    -0.58
    POSITIVE LOGITS
    OUS
    1.11
    AMI
    1.09
    YA
    1.08
    KE
    1.04
    BILITY
    1.04
    ALLY
    0.99
    RECT
    0.99
    BA
    0.98
    ANS
    0.97
    WI
    0.97
    Activations Density 0.031%

    No Known Activations