© 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. 6860
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving an idea or sense of something

    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
    413
    +0.12
    0.5%
    513
    +0.11
    0.5%
    62
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    413
    +0.12
    0.04
    513
    +0.11
    0.03
    39
    +0.10
    0.03
    Negative Logits
     Bulgar
    -0.65
    iki
    -0.65
     Carbuncle
    -0.61
     Budapest
    -0.61
    die
    -0.57
     Klux
    -0.56
     withdrawn
    -0.55
     Cosmos
    -0.55
     chants
    -0.55
    bees
    -0.55
    POSITIVE LOGITS
     impression
    0.92
     thereof
    0.92
     ballpark
    0.89
     approximation
    0.89
     outline
    0.87
     indication
    0.85
     glimpse
    0.83
     estimate
    0.81
    imate
    0.78
     overview
    0.78
    Activations Density 0.127%

    No Known Activations