© 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 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. 10828
    Prev
    Next
    INDEX
    Explanations

    entities related to educational institutions

    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
    481
    +0.15
    0.7%
    447
    +0.12
    0.6%
    114
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.15
    0.05
    146
    +0.12
    0.05
    114
    +0.10
    0.05
    Negative Logits
    tein
    -0.73
    bush
    -0.70
    lihood
    -0.64
     hallucinations
    -0.64
    hunt
    -0.62
    kun
    -0.62
    ifest
    -0.62
    otos
    -0.60
    iasis
    -0.60
    Condition
    -0.60
    POSITIVE LOGITS
    chool
    1.03
     nationwide
    0.94
    hips
    0.93
    mith
    0.88
    ystem
    0.87
    hare
    0.87
    folk
    0.86
    afety
    0.82
    '
    0.80
    ensor
    0.79
    Activations Density 0.203%

    No Known Activations