© 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. 7789
    Prev
    Next
    INDEX
    Explanations

    conspiracy-related terms and phrases

    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
    746
    +0.13
    0.6%
    288
    +0.12
    0.5%
    681
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    746
    +0.13
    0.02
    681
    +0.12
    0.02
    32
    +0.11
    0.02
    Negative Logits
    ijk
    -0.82
    Thom
    -0.77
    inished
    -0.74
    older
    -0.69
     Chop
    -0.69
    oba
    -0.68
    esa
    -0.66
    TD
    -0.65
    zl
    -0.65
    isha
    -0.64
    POSITIVE LOGITS
     theorist
    1.47
     theorists
    1.45
     theories
    1.34
     theory
    1.06
     theor
    1.02
    ulent
    0.96
     conspir
    0.93
     conspiracy
    0.93
    eering
    0.92
     hatched
    0.88
    Activations Density 0.021%

    No Known Activations