© 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. 9696
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and political entities, particularly related to borders and constructions

    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
    480
    +0.37
    1.9%
    481
    +0.20
    1.0%
    447
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.37
    0.08
    480
    +0.20
    0.03
    288
    +0.20
    0.10
    Negative Logits
    ÃįÃį
    -0.57
     awa
    -0.56
     corrid
    -0.54
    pload
    -0.54
     notor
    -0.53
    ãĤĮ
    -0.52
    ÙĦ
    -0.52
    ãĤª
    -0.51
    ãĥ³ãĤ¸
    -0.51
    åŃ
    -0.50
    POSITIVE LOGITS
     Copyright
    0.77
     Belfast
    0.74
     Shutterstock
    0.71
    ↵
    0.70
     ©
    0.66
     Posted
    0.65
    utterstock
    0.64
    ↵Âł
    0.64
    ¶
    0.63
    ↵↵
    0.63
    Activations Density 0.664%

    No Known Activations