© 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. 20497
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of belonging and community

    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
    640
    +0.20
    0.9%
    618
    +0.10
    0.5%
    64
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.09
    6
    +0.10
    0.07
    64
    +0.10
    -0.02
    Negative Logits
     unin
    -0.75
     toler
    -0.73
     estranged
    -0.72
     unsc
    -0.71
    ibrary
    -0.71
     printing
    -0.69
    etheless
    -0.69
     agon
    -0.68
     inconvenient
    -0.68
     composing
    -0.67
    POSITIVE LOGITS
    Interview
    1.26
    Question
    1.21
    Narr
    1.16
    Yeah
    1.14
    Asked
    1.13
    Anyway
    1.11
    Were
    1.07
    Talking
    1.07
    AMY
    1.07
    QUEST
    1.06
    Activations Density 0.240%

    No Known Activations