© 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. 10276
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of time and its impact on various topics, such as evolution, business decisions, societal changes, and personal experiences

    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
    726
    +0.12
    0.5%
    76
    +0.11
    0.5%
    724
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.12
    0.03
    724
    +0.11
    0.02
    76
    +0.11
    0.02
    Negative Logits
    hest
    -0.72
    Bey
    -0.68
     Hats
    -0.68
     ensu
    -0.67
    mosp
    -0.65
    insula
    -0.65
     Parties
    -0.64
    awan
    -0.63
    jah
    -0.62
    Hub
    -0.62
    POSITIVE LOGITS
    frames
    1.08
     periods
    0.89
     iterations
    0.86
     horizon
    0.81
     generations
    0.79
     ILCS
    0.77
     cycles
    0.75
     continuum
    0.73
    VERTISEMENT
    0.71
     conditioning
    0.69
    Activations Density 0.051%

    No Known Activations