© 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. 8096
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender issues

    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
    192
    +0.12
    0.5%
    123
    +0.11
    0.5%
    703
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.12
    0.07
    22
    +0.11
    0.06
    29
    +0.11
    0.06
    Negative Logits
    USB
    -0.80
    wcsstore
    -0.76
    leeve
    -0.72
    atel
    -0.70
    BUS
    -0.70
    #$
    -0.68
     pains
    -0.68
    LOD
    -0.68
    tre
    -0.67
    801
    -0.66
    POSITIVE LOGITS
     lieu
    1.20
    effic
    1.17
     relation
    1.12
     accordance
    1.06
    efficiency
    1.03
     general
    1.02
     America
    1.02
     academia
    0.98
    clus
    0.97
     society
    0.96
    Activations Density 0.238%

    No Known Activations