© 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. 22002
    Prev
    Next
    INDEX
    Explanations

    discussion points or arguments revolving around the Electoral College system

    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
    373
    +0.16
    0.7%
    668
    +0.09
    0.4%
    213
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    668
    +0.16
    0.03
    14
    +0.09
    0.03
    20
    +0.09
    0.03
    Negative Logits
     plotting
    -0.74
     projecting
    -0.66
     wasting
    -0.66
     preparing
    -0.66
     supplying
    -0.65
     aiming
    -0.64
     distributing
    -0.64
     framing
    -0.63
     administering
    -0.63
     sending
    -0.63
    POSITIVE LOGITS
     been
    1.30
    been
    1.16
     arisen
    1.11
     Been
    1.11
     emerged
    0.93
     existed
    0.92
    bara
    0.90
    Ŀ
    0.88
    kell
    0.85
     transpired
    0.81
    Activations Density 0.047%

    No Known Activations