© 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. 18459
    Prev
    Next
    INDEX
    Explanations

    references to distances and locations

    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
    413
    +0.12
    0.6%
    479
    +0.11
    0.5%
    565
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    565
    +0.12
    0.04
    238
    +0.11
    0.04
    344
    +0.11
    0.04
    Negative Logits
    acus
    -0.74
    olin
    -0.70
    orian
    -0.67
    odic
    -0.66
    erity
    -0.64
    illions
    -0.63
    orians
    -0.62
    ole
    -0.62
    olar
    -0.62
    inous
    -0.61
    POSITIVE LOGITS
     southwest
    1.13
     southeast
    1.12
     northeast
    1.07
     northwest
    1.06
     east
    1.00
    outheast
    1.00
     west
    0.96
     south
    0.94
     north
    0.94
     outskirts
    0.85
    Activations Density 0.107%

    No Known Activations