© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6131
    Prev
    Next
    INDEX
    Explanations

    political entities and power dynamics

    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
    420
    +0.11
    0.5%
    168
    +0.10
    0.5%
    711
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.11
    0.03
    344
    +0.10
    0.05
    242
    +0.10
    0.04
    Negative Logits
     experimentation
    -0.70
     unforeseen
    -0.70
     unexpected
    -0.67
     culminating
    -0.67
     finally
    -0.66
    hemer
    -0.65
     unleashed
    -0.65
     culminated
    -0.64
     unveiled
    -0.64
     gradual
    -0.63
    POSITIVE LOGITS
    âĺ
    0.85
    \)
    0.77
    76561
    0.76
     adjoining
    0.72
     neighbouring
    0.70
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.70
    %%
    0.69
    rador
    0.69
     nearby
    0.69
     constituency
    0.67
    Activations Density 0.662%

    No Known Activations