© 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. 7598
    Prev
    Next
    INDEX
    Explanations

    phrases related to caring for and supporting others

    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
    420
    +0.12
    0.5%
    314
    +0.11
    0.5%
    35
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.02
    4
    +0.11
    0.02
    424
    +0.10
    0.02
    Negative Logits
    ãĥĥãĥī
    -0.85
    ãĥ³ãĤ¸
    -0.78
    kered
    -0.71
     bluff
    -0.70
    âĸ¬
    -0.69
     rand
    -0.67
     IGN
    -0.64
    âĸ¬âĸ¬
    -0.62
    akedown
    -0.62
    lihood
    -0.61
    POSITIVE LOGITS
    taker
    1.70
    giving
    1.32
    taking
    1.21
    lessness
    1.03
    fully
    1.02
    tta
    1.01
    ening
    0.99
    free
    0.97
    lessly
    0.96
    ful
    0.88
    Activations Density 0.026%

    No Known Activations