© 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 EvalsExportsinterp-engineNEWAPI 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. 16022
    Prev
    Next
    INDEX
    Explanations

    words related to honesty and fairness

    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
    373
    +0.15
    0.7%
    274
    +0.11
    0.5%
    134
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.15
    0.02
    155
    +0.11
    0.02
    452
    +0.10
    0.02
    Negative Logits
    borough
    -0.64
     decom
    -0.61
     Written
    -0.60
     dissolve
    -0.59
    und
    -0.59
     lin
    -0.58
    eller
    -0.58
    åĮ
    -0.57
    mult
    -0.56
    arnaev
    -0.55
    POSITIVE LOGITS
    ipop
    0.75
     though
    0.73
     there
    0.64
    iosis
    0.62
    eno
    0.62
    oin
    0.62
    ION
    0.61
    iona
    0.60
    oops
    0.59
     here
    0.58
    Activations Density 0.053%

    No Known Activations