© 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. 17069
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and assistance

    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
    +0.34
    1.7%
    447
    +0.31
    1.6%
    480
    +0.25
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.34
    0.06
    266
    +0.31
    0.07
    480
    +0.25
    0.01
    Negative Logits
     advoc
    -0.65
     arrang
    -0.64
    hovah
    -0.63
     destro
    -0.63
    Ò
    -0.61
     undermin
    -0.61
     withd
    -0.60
     thereof
    -0.60
    akespe
    -0.60
     cryst
    -0.59
    POSITIVE LOGITS
     Profile
    1.17
     âĵĺ
    0.83
    ¶
    0.83
     Brewing
    0.80
     Releases
    0.78
     Overview
    0.77
     Gets
    0.76
    âĦ¢
    0.75
    ®
    0.75
     Facts
    0.72
    Activations Density 0.527%

    No Known Activations