© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18750
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and infidelity, including terms like "polygamy" and "monogamy."

    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
    269
    +0.14
    0.6%
    216
    +0.11
    0.5%
    492
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    48
    +0.11
    0.01
    577
    +0.09
    0.01
    Negative Logits
     Nerd
    -0.75
     Discovery
    -0.73
    went
    -0.71
     Despair
    -0.70
     Cheong
    -0.69
     Dive
    -0.69
     Valencia
    -0.69
     FEMA
    -0.67
     Blizz
    -0.67
     Jagu
    -0.66
    POSITIVE LOGITS
    amous
    1.05
    asma
    0.91
    atform
    0.87
    gon
    0.83
    astically
    0.81
    icate
    0.78
    omial
    0.77
     polyg
    0.77
    icable
    0.77
    thood
    0.76
    Activations Density 0.025%

    No Known Activations