© 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. 37477
    Prev
    Next
    INDEX
    Explanations

    political and social references related to authority and identity issues

    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
    30
    +0.10
    0.5%
    264
    +0.09
    0.4%
    363
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.10
    0.04
    264
    +0.09
    0.03
    365
    +0.09
    0.01
    Negative Logits
    ãĤ·ãĥ£
    -0.67
    ++++++++++++++++
    -0.65
    à¥
    -0.64
    DragonMagazine
    -0.64
    ¶
    -0.64
     ðŁij
    -0.63
     ðŁ
    -0.61
    KT
    -0.61
    ðŁij
    -0.59
     âľ
    -0.58
    POSITIVE LOGITS
     alike
    1.05
     respectively
    0.95
     versa
    0.93
     thereto
    0.89
     thereafter
    0.88
     consequ
    0.85
     subsequent
    0.82
     therein
    0.81
     thereof
    0.80
     consequently
    0.72
    Activations Density 0.438%

    No Known Activations