© 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. 8992
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or difficulties

    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
    458
    +0.13
    0.6%
    737
    +0.12
    0.5%
    354
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.13
    0.03
    737
    +0.12
    0.03
    633
    +0.12
    0.02
    Negative Logits
     fragments
    -0.83
    ioxide
    -0.81
     typh
    -0.81
     beads
    -0.75
     flakes
    -0.74
     projectiles
    -0.72
     images
    -0.72
     grains
    -0.72
     imagery
    -0.72
     batches
    -0.71
    POSITIVE LOGITS
     delegated
    0.90
     hers
    0.87
     vacated
    0.86
     reserved
    0.86
     conferred
    0.85
     bestowed
    0.85
     vacant
    0.83
     overseeing
    0.79
     specialization
    0.79
     holder
    0.78
    Activations Density 0.217%

    No Known Activations