© 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. 2477
    Prev
    Next
    INDEX
    Explanations

    words related to news and current events, particularly focused on specific locations or individuals

    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
    614
    +0.14
    0.7%
    314
    +0.12
    0.6%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    614
    +0.14
    0.03
    572
    +0.12
    0.03
    610
    +0.10
    0.02
    Negative Logits
     sorts
    -0.70
    âĸº
    -0.64
     places
    -0.63
     minus
    -0.62
     jeopardy
    -0.60
    è¯
    -0.60
     spots
    -0.60
     Continued
    -0.58
     Jenner
    -0.58
    âĶĢ
    -0.58
    POSITIVE LOGITS
    omaly
    1.40
    alys
    1.36
    alogue
    1.33
    alyses
    1.28
    notation
    1.22
    omal
    1.21
    terior
    1.20
    ubis
    1.19
    nette
    1.16
    alysed
    1.13
    Activations Density 0.035%

    No Known Activations