© 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 49152
    5. 8-RES_FS49152-JB
    6. 41474
    Prev
    Next
    INDEX
    Explanations

    quantifiers and terms related to quantities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    71
    +0.11
    0.5%
    668
    +0.09
    0.4%
    148
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.11
    0.04
    344
    +0.09
    0.04
    748
    +0.09
    0.03
    Negative Logits
    uncture
    -0.80
    nature
    -0.78
    someone
    -0.71
    abad
    -0.70
    hani
    -0.67
    ennis
    -0.67
    asion
    -0.66
    iosis
    -0.65
    terness
    -0.65
     Ruler
    -0.64
    POSITIVE LOGITS
     prototypes
    0.99
     copies
    0.97
     packages
    0.94
     variants
    0.92
     versions
    0.91
     leaflets
    0.90
     proposals
    0.90
     batches
    0.88
     instances
    0.86
     chapters
    0.86
    Activations Density 0.148%

    No Known Activations