© 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. 22048
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or environmental conditions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    480
    +0.43
    2.1%
    266
    +0.11
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.43
    0.01
    266
    +0.11
    0.09
    517
    +0.10
    0.05
    Negative Logits
    oyal
    -0.81
    aughs
    -0.71
    erity
    -0.65
    ealous
    -0.64
    PDATE
    -0.63
     acknowled
    -0.62
    ãĥĹ
    -0.62
    aughed
    -0.60
    OUP
    -0.60
     Mehran
    -0.59
    POSITIVE LOGITS
     inhabited
    1.12
     zones
    1.03
     habitats
    0.98
     caves
    0.98
     landscapes
    0.97
     terrain
    0.97
     populated
    0.97
     continents
    0.96
     neighborhoods
    0.96
     habitable
    0.96
    Activations Density 0.955%

    No Known Activations