© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10532
    Prev
    Next
    INDEX
    Explanations

    phrases related to political news and criminal activities

    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
    447
    +0.27
    1.3%
    481
    +0.12
    0.6%
    258
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.27
    0.08
    258
    +0.12
    0.06
    575
    +0.12
    0.05
    Negative Logits
    ãĤ¨ãĥ«
    -0.85
    YN
    -0.77
    odox
    -0.75
    æ©
    -0.72
    STD
    -0.69
    onom
    -0.68
    anger
    -0.68
    é¾įåĸļ士
    -0.68
    Hug
    -0.67
    irlf
    -0.65
    POSITIVE LOGITS
    ®,
    0.81
     syndrome
    0.79
     deployments
    0.77
    ®
    0.74
    âĦ¢
    0.72
     runoff
    0.71
     aka
    0.69
     candidacy
    0.67
     equivalents
    0.67
     hegemony
    0.67
    Activations Density 0.329%

    No Known Activations