© 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 1536
    9. 8-RES_FS1536-JB
    11. 1065
    Prev
    Next
    INDEX
    Explanations

    phrases related to security measures and arrangements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    355
    +0.14
    0.6%
    277
    +0.11
    0.5%
    637
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.14
    0.14
    402
    +0.11
    0.11
    362
    +0.09
    0.13
    Negative Logits
    apego
    -0.69
    inx
    -0.66
    ulner
    -0.66
    itiz
    -0.62
    ourge
    -0.61
    ographers
    -0.61
     Yorkers
    -0.59
    ahi
    -0.59
     brakes
    -0.58
    paio
    -0.58
    POSITIVE LOGITS
     guise
    1.25
     manner
    1.19
     vicinity
    1.17
     context
    1.12
     nutshell
    1.11
     vein
    1.10
     contexts
    1.05
     fashion
    1.04
     circles
    1.03
     midst
    1.03
    Activations Density 3.614%

    No Known Activations