© 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. 8546
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly ports

    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
    +0.14
    0.6%
    288
    +0.12
    0.5%
    238
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.14
    0.02
    238
    +0.12
    0.02
    607
    +0.11
    0.01
    Negative Logits
    pta
    -0.71
    IGHTS
    -0.69
    ãĥ©ãĥ³
    -0.67
     toget
    -0.66
    soever
    -0.64
    ById
    -0.62
     Dying
    -0.61
     Matter
    -0.61
    IGH
    -0.60
    Interstitial
    -0.60
    POSITIVE LOGITS
    ugal
    1.29
    folio
    1.29
    folios
    1.24
    rait
    1.14
    raits
    1.00
    eur
    0.95
    iously
    0.81
    itional
    0.79
    ilage
    0.78
     forwarding
    0.78
    Activations Density 0.014%

    No Known Activations