© 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. 12083
    Prev
    Next
    INDEX
    Explanations

    phrases related to distributed energy sources such as solar power and distributed computing

    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
    288
    +0.13
    0.6%
    167
    +0.12
    0.6%
    615
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    615
    +0.13
    0.01
    597
    +0.12
    0.01
    31
    +0.11
    0.01
    Negative Logits
    glers
    -1.21
    swick
    -0.86
    tes
    -0.77
     Cage
    -0.74
    ppo
    -0.74
    ENA
    -0.70
    çĦ
    -0.69
     ABE
    -0.66
    manship
    -0.66
     Twice
    -0.65
    POSITIVE LOGITS
    ribut
    1.58
    ributed
    1.53
    ribution
    1.51
    rict
    1.43
    ribute
    1.40
    inguished
    1.34
    raction
    1.33
    illery
    1.26
    ortion
    1.25
    inct
    1.25
    Activations Density 0.010%

    No Known Activations