© 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. 18278
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical communication and decision-making

    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
    447
    +0.22
    1.0%
    459
    +0.12
    0.6%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.22
    0.11
    575
    +0.12
    0.10
    288
    +0.11
    0.11
    Negative Logits
    ©¶æ
    -0.72
     ?)
    -0.72
     )]
    -0.65
    etheless
    -0.63
    =]
    -0.58
     Schwar
    -0.56
    çīĪ
    -0.54
     Canaver
    -0.54
    ?).
    -0.54
    THER
    -0.53
    POSITIVE LOGITS
     whereas
    1.08
     whilst
    0.93
    .
    0.93
    ;
    0.90
     because
    0.89
     unless
    0.87
     regardless
    0.81
     while
    0.78
     irrespective
    0.78
    .;
    0.77
    Activations Density 1.043%

    No Known Activations