© 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. 16274
    Prev
    Next
    INDEX
    Explanations

    references to the concept of messengers or messages being delivered

    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
    526
    +0.12
    0.6%
    377
    +0.12
    0.6%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.12
    0.01
    377
    +0.12
    0.02
    48
    +0.10
    0.01
    Negative Logits
    undai
    -0.80
    eele
    -0.78
     livest
    -0.77
    vation
    -0.74
    cember
    -0.74
    cki
    -0.73
    ©¶æ
    -0.69
    GRE
    -0.67
    éĸ
    -0.64
     Warrant
    -0.64
    POSITIVE LOGITS
    engers
    1.69
    enger
    1.20
    iah
    1.19
    aging
    1.17
    aged
    1.06
    ages
    0.99
    iness
    0.90
    INESS
    0.90
    es
    0.89
    alos
    0.82
    Activations Density 0.031%

    No Known Activations