© 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 49152
    9. 8-RES_FS49152-JB
    11. 45621
    Prev
    Next
    INDEX
    Explanations

    mentions of the day "Friday" in various contexts

    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
    430
    +0.16
    0.7%
    726
    +0.12
    0.6%
    384
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.16
    0.05
    384
    +0.12
    0.04
    662
    +0.10
    0.04
    Negative Logits
    ership
    -0.97
    hip
    -0.82
    aeda
    -0.72
    vironment
    -0.72
    arist
    -0.69
    ator
    -0.69
    atche
    -0.69
    ATOR
    -0.68
    estern
    -0.67
    itton
    -0.67
    POSITIVE LOGITS
     afternoon
    1.52
     morning
    1.49
     night
    1.38
     evening
    1.34
     mornings
    1.30
     nights
    1.15
     Night
    1.12
     evenings
    1.05
    night
    0.98
    morning
    0.96
    Activations Density 0.023%

    No Known Activations