© 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. 276
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social issues surrounding 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_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
    756
    +0.12
    0.6%
    712
    +0.10
    0.5%
    682
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.10
    756
    +0.10
    -0.01
    184
    +0.10
    0.04
    Negative Logits
     horm
    -0.70
    CTV
    -0.66
     chatting
    -0.64
     hobbies
    -0.63
     fascinating
    -0.62
     intrigue
    -0.62
     myself
    -0.61
     versatility
    -0.60
     coma
    -0.59
     chatter
    -0.59
    POSITIVE LOGITS
     theirs
    0.86
     unilaterally
    0.76
    )).
    0.74
    ccess
    0.70
     veto
    0.70
     its
    0.70
     enforce
    0.69
     itself
    0.68
     enforcing
    0.68
    Its
    0.66
    Activations Density 0.814%

    No Known Activations