© 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 49152
    9. 8-RES_FS49152-JB
    11. 26674
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and product quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.28
    1.3%
    388
    +0.13
    0.6%
    134
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.04
    388
    +0.13
    0.03
    678
    +0.11
    0.02
    Negative Logits
    âĹ¼
    -0.70
    NetMessage
    -0.64
    actionDate
    -0.60
     fetal
    -0.56
     AAA
    -0.55
     nond
    -0.55
     AQ
    -0.55
    Ô
    -0.54
     Baghd
    -0.53
     ageing
    -0.53
    POSITIVE LOGITS
    icult
    0.72
    otype
    0.70
    icles
    0.69
    imity
    0.67
    icle
    0.66
     featuring
    0.64
    ourse
    0.64
    code
    0.64
     whose
    0.64
    cade
    0.64
    Activations Density 0.125%

    No Known Activations