© 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. 9163
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining consistency or control

    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
    642
    +0.14
    0.6%
    567
    +0.13
    0.6%
    515
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.14
    0.02
    567
    +0.13
    0.02
    515
    +0.11
    0.02
    Negative Logits
    NetMessage
    -0.81
    DragonMagazine
    -0.77
    mes
    -0.70
    gey
    -0.70
    onz
    -0.67
    çīĪ
    -0.67
    ologue
    -0.65
    UGC
    -0.63
    gom
    -0.61
    bid
    -0.61
    POSITIVE LOGITS
     composure
    1.03
     secrecy
    0.91
     stability
    0.91
     vigil
    0.91
     confidentiality
    0.89
     vigilance
    0.88
     momentum
    0.86
     equilibrium
    0.84
     continuity
    0.84
    ably
    0.83
    Activations Density 0.033%

    No Known Activations