© 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. 11948
    Prev
    Next
    INDEX
    Explanations

    words related to deception or dishonesty

    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
    240
    +0.10
    0.5%
    99
    +0.10
    0.4%
    119
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.01
    409
    +0.10
    0.01
    240
    +0.10
    0.01
    Negative Logits
    interrupted
    -0.82
    nas
    -0.72
    IO
    -0.69
    ENTS
    -0.69
    LESS
    -0.67
    YL
    -0.67
    ians
    -0.67
    cake
    -0.66
    IAN
    -0.65
    upon
    -0.65
    POSITIVE LOGITS
    azy
    1.28
    eker
    1.08
    igh
    1.05
    uth
    0.97
    eper
    0.93
    asure
    0.90
    avement
    0.89
    pload
    0.87
    aving
    0.85
    aping
    0.84
    Activations Density 0.019%

    No Known Activations