© 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. 1898
    Prev
    Next
    INDEX
    Explanations

    information related to land use, planning, zoning regulations, and conservation acts

    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
    288
    +0.15
    0.7%
    737
    +0.11
    0.5%
    76
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.15
    0.03
    152
    +0.11
    0.03
    76
    +0.10
    0.03
    Negative Logits
    vernment
    -0.78
    ector
    -0.70
     Universe
    -0.65
     Fior
    -0.65
    hift
    -0.64
    asio
    -0.62
    èĢħ
    -0.61
     Mori
    -0.61
    chio
    -0.60
    Vo
    -0.59
    POSITIVE LOGITS
    owner
    1.21
    locked
    1.20
    mass
    1.08
    scape
    0.99
    mine
    0.99
    owners
    0.95
    holder
    0.91
    grave
    0.90
    holders
    0.90
    lot
    0.87
    Activations Density 0.028%

    No Known Activations