© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19617
    Prev
    Next
    INDEX
    Explanations

    phrases related to shipbuilding and naval vessels

    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
    459
    +0.13
    0.6%
    484
    +0.11
    0.5%
    160
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    652
    +0.13
    0.02
    484
    +0.11
    0.02
    459
    +0.10
    0.02
    Negative Logits
    âĶģ
    -0.92
    çīĪ
    -0.84
    theless
    -0.70
    66666666
    -0.69
    ADRA
    -0.68
    okers
    -0.67
    osate
    -0.67
     tremend
    -0.64
     confir
    -0.64
    ums
    -0.62
    POSITIVE LOGITS
    wreck
    1.83
    yard
    1.41
    wright
    1.33
    yards
    1.26
    building
    1.16
    shape
    1.15
    builders
    1.09
     Graveyard
    1.08
    boat
    1.06
     sailed
    1.05
    Activations Density 0.028%

    No Known Activations