© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18713
    Prev
    Next
    INDEX
    Explanations

    references related to bells or ringing bells

    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
    16
    +0.10
    0.4%
    732
    +0.10
    0.4%
    352
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.10
    0.01
    326
    +0.10
    0.01
    748
    +0.10
    0.01
    Negative Logits
    ©¶æ
    -0.81
    xual
    -0.69
    ritz
    -0.67
     Agents
    -0.66
    raviolet
    -0.65
    isoft
    -0.65
    ensual
    -0.65
    VICE
    -0.64
    eki
    -0.64
     unpre
    -0.64
    POSITIVE LOGITS
     bells
    1.12
    bell
    1.06
     ringing
    1.02
    ows
    1.00
     bell
    0.92
    owed
    0.87
    iod
    0.86
    tower
    0.85
     rang
    0.84
    flower
    0.81
    Activations Density 0.021%

    No Known Activations