© 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. 16679
    Prev
    Next
    INDEX
    Explanations

    words related to media and news reporting

    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
    392
    +0.11
    0.5%
    503
    +0.11
    0.5%
    251
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.11
    0.03
    251
    +0.11
    0.02
    503
    +0.11
    0.02
    Negative Logits
    âĸ¬âĸ¬
    -0.70
    ĪĴ
    -0.68
    İĭ
    -0.68
    ĸļ
    -0.63
     Brotherhood
    -0.62
     Fathers
    -0.61
     behold
    -0.61
    naires
    -0.60
    phis
    -0.60
     Nou
    -0.60
    POSITIVE LOGITS
    aghetti
    1.22
    iral
    1.22
    oiler
    1.18
    atial
    1.15
    ooky
    1.07
    aces
    1.05
    ending
    1.04
    acing
    1.01
    inning
    1.00
    iegel
    1.00
    Activations Density 0.018%

    No Known Activations