© 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. 20698
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people's names, possibly related to news or events

    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
    481
    +0.15
    0.7%
    502
    +0.11
    0.5%
    547
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.08
    502
    +0.11
    0.07
    700
    +0.10
    0.07
    Negative Logits
     robbers
    -0.68
     WOM
    -0.62
     bandits
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.60
     phantom
    -0.60
     foreigners
    -0.59
     disappearing
    -0.59
     Glac
    -0.59
     strangers
    -0.58
     vanishing
    -0.58
    POSITIVE LOGITS
     oversaw
    0.99
     Jr
    0.98
     told
    0.98
     oversees
    0.97
     said
    0.96
     commented
    0.92
    meier
    0.91
     cautioned
    0.91
     acknowledged
    0.90
    baum
    0.90
    Activations Density 0.242%

    No Known Activations