© 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. 18733
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives related to size and quantity

    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
    487
    +0.11
    0.5%
    623
    +0.10
    0.4%
    65
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.11
    0.04
    623
    +0.10
    0.03
    669
    +0.09
    0.03
    Negative Logits
    WP
    -0.78
    shire
    -0.75
    odor
    -0.71
     Immun
    -0.71
    hire
    -0.69
    ION
    -0.69
    EVA
    -0.69
    EP
    -0.68
    syn
    -0.66
    ���
    -0.66
    POSITIVE LOGITS
     than
    1.35
    than
    1.18
     Than
    1.16
     diameter
    1.08
     sized
    1.01
     sizes
    0.98
     quantities
    0.93
     scale
    0.91
     stature
    0.89
     size
    0.84
    Activations Density 0.049%

    No Known Activations