© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 22081
    Prev
    Next
    INDEX
    Explanations

    phrases related to human interactions and social considerations

    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
    591
    +0.11
    0.5%
    584
    +0.11
    0.5%
    378
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.05
    583
    +0.11
    0.04
    38
    +0.10
    0.04
    Negative Logits
     predecessor
    -0.97
     srfAttach
    -0.94
     successor
    -0.80
    ãĤ¢ãĥ«
    -0.71
     Implementation
    -0.71
     counterpart
    -0.70
    è£ħ
    -0.67
    ãĥķãĤ©
    -0.65
    é¾įå¥ij士
    -0.65
     overseen
    -0.65
    POSITIVE LOGITS
     clam
    0.93
     misunderstand
    0.92
     confuse
    0.85
     perceive
    0.85
     grav
    0.81
     misconception
    0.80
     hating
    0.80
     underestimate
    0.79
     misinterpret
    0.79
     gull
    0.78
    Activations Density 0.317%

    No Known Activations