© 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. 11087
    Prev
    Next
    INDEX
    Explanations

    places and establishments

    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
    225
    +0.11
    0.5%
    110
    +0.11
    0.5%
    145
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.11
    0.05
    24
    +0.11
    0.05
    693
    +0.10
    0.05
    Negative Logits
     regulators
    -0.67
    theless
    -0.66
     gamers
    -0.66
     wise
    -0.65
     embodiments
    -0.65
     consumers
    -0.64
     numer
    -0.64
     matters
    -0.63
     differentiated
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
     Hotel
    1.27
     Lounge
    1.16
     Awards
    1.10
     Complex
    1.06
     Café
    1.03
     Estate
    1.02
     Observatory
    0.99
     Cafe
    0.97
     Theatre
    0.97
     Facility
    0.97
    Activations Density 0.268%

    No Known Activations