© 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. 12074
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or abundance

    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
    71
    +0.17
    0.8%
    393
    +0.15
    0.7%
    608
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.17
    0.03
    344
    +0.15
    0.03
    608
    +0.13
    0.03
    Negative Logits
    acus
    -0.96
    ĸļ
    -0.84
    ħĭ
    -0.79
    most
    -0.78
    gypt
    -0.75
    ESE
    -0.75
    ²¾
    -0.72
    era
    -0.72
    stal
    -0.71
    ree
    -0.70
    POSITIVE LOGITS
     opportunities
    1.11
     surprises
    1.07
     unanswered
    1.00
     interesting
    0.91
     anecdotal
    0.90
     positives
    0.90
     examples
    0.89
     juicy
    0.89
     parallels
    0.88
     excuses
    0.88
    Activations Density 0.062%

    No Known Activations