© 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. 6715
    Prev
    Next
    INDEX
    Explanations

    words related to deals or discounts

    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
    531
    +0.11
    0.5%
    119
    +0.11
    0.5%
    300
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    531
    +0.11
    0.01
    288
    +0.11
    0.01
    326
    +0.09
    0.01
    Negative Logits
    onso
    -0.80
    ocrates
    -0.77
     Cheong
    -0.75
    iferation
    -0.74
    mos
    -0.74
    bert
    -0.73
    armac
    -0.72
    pora
    -0.72
    andre
    -0.72
    lav
    -0.72
    POSITIVE LOGITS
     barg
    1.24
     bargain
    1.22
     Barg
    1.07
     basement
    0.96
     bargaining
    0.92
     breaker
    0.78
    ably
    0.78
    eer
    0.74
     bins
    0.70
    ged
    0.69
    Activations Density 0.027%

    No Known Activations