© 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. 2098
    Prev
    Next
    INDEX
    Explanations

    topics related to political or social issues around the world

    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
    +0.15
    0.7%
    459
    +0.14
    0.6%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.07
    459
    +0.14
    0.05
    575
    +0.10
    0.06
    Negative Logits
    otal
    -0.72
    akespeare
    -0.70
    anuts
    -0.64
    vag
    -0.62
    enged
    -0.58
    ealous
    -0.56
     OTHER
    -0.56
    SPONSORED
    -0.55
     poor
    -0.55
    aceae
    -0.54
    POSITIVE LOGITS
     arrivals
    0.85
     hires
    0.78
    stadt
    0.78
    anding
    0.74
     additions
    0.73
     entrants
    0.70
     paradigm
    0.69
     architectures
    0.66
     hire
    0.66
     complication
    0.65
    Activations Density 0.395%

    No Known Activations