© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 12490
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a contrast or connection between different ideas or elements

    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
    393
    +0.12
    0.5%
    353
    +0.10
    0.4%
    737
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.04
    456
    +0.10
    0.03
    239
    +0.10
    0.03
    Negative Logits
    swick
    -1.02
    EStream
    -0.85
    FactoryReloaded
    -0.81
    PsyNetMessage
    -0.78
    roups
    -0.78
    ESA
    -0.73
    RPG
    -0.73
    ãĤ§
    -0.71
    iannopoulos
    -0.71
    YS
    -0.71
    POSITIVE LOGITS
     unamb
    1.05
     unmist
    1.05
     unequiv
    1.04
     concise
    0.99
    rogen
    0.98
     emph
    0.90
     undeniable
    0.89
     uninterrupted
    0.88
     forceful
    0.88
     abiding
    0.87
    Activations Density 0.115%

    No Known Activations