© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1991
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to coding and software development

    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
    326
    +0.12
    0.6%
    167
    +0.11
    0.5%
    641
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.05
    314
    +0.11
    0.01
    659
    +0.10
    0.05
    Negative Logits
     Rasmussen
    -0.74
     nationally
    -0.74
     airing
    -0.73
     Noel
    -0.72
     tha
    -0.72
     afore
    -0.71
     striking
    -0.69
     totality
    -0.69
     Nationwide
    -0.69
     Volks
    -0.68
    POSITIVE LOGITS
    Config
    1.24
    SQL
    1.22
    Debug
    1.17
    Install
    1.17
    Server
    1.15
    Query
    1.11
    Proxy
    1.10
    VM
    1.08
    stack
    1.08
    Client
    1.08
    Activations Density 0.263%

    No Known Activations