© 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 12288
    9. 8-RES_FS12288-JB
    11. 1630
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement, legal matters, and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    656
    +0.13
    0.6%
    762
    +0.13
    0.6%
    735
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.13
    0.12
    656
    +0.13
    0.07
    146
    +0.12
    0.07
    Negative Logits
    Ñı
    -0.68
     srfAttach
    -0.66
     Journey
    -0.66
    rencies
    -0.62
    uania
    -0.62
     Estonia
    -0.62
    urst
    -0.61
     sqor
    -0.61
     Latvia
    -0.61
    reenshots
    -0.61
    POSITIVE LOGITS
     intervened
    1.10
     forb
    1.02
     intervene
    1.01
     disappro
    0.98
     swoop
    0.97
     coax
    0.92
     decre
    0.91
     forbid
    0.89
     intervention
    0.89
     dictates
    0.88
    Activations Density 1.281%

    No Known Activations