© 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 EvalsExportsinterp-engineNEWAPI 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. 4794
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames and messages related to support for causes or communities

    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
    683
    +0.10
    0.4%
    203
    +0.10
    0.4%
    39
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.10
    0.01
    659
    +0.10
    0.01
    30
    +0.10
    0.01
    Negative Logits
     Takeru
    -0.78
     disadvantage
    -0.70
     shaping
    -0.66
    selection
    -0.65
     tampering
    -0.64
     consolidation
    -0.63
     conceal
    -0.63
    iris
    -0.62
     tract
    -0.62
     disadvantages
    -0.61
    POSITIVE LOGITS
     (@
    1.65
     @
    1.11
    ($
    0.94
     (/
    0.92
     (%
    0.91
    (_
    0.88
     <+
    0.87
    (&
    0.85
     (_
    0.84
     Blog
    0.84
    Activations Density 0.024%

    No Known Activations