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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7386
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological advancements and developments

    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
    87
    +0.22
    1.1%
    470
    +0.13
    0.6%
    157
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.22
    0.06
    718
    +0.13
    0.07
    596
    +0.10
    0.05
    Negative Logits
     ('
    -0.65
    iability
    -0.63
     substituted
    -0.62
     murdered
    -0.62
     murd
    -0.61
     wra
    -0.61
     (>
    -0.60
     ignor
    -0.60
     murdering
    -0.60
     sacrific
    -0.60
    POSITIVE LOGITS
     prompted
    0.74
     spurred
    0.69
    quickShipAvailable
    0.68
     contentious
    0.68
     bolstered
    0.66
     bipartisan
    0.66
     broader
    0.65
    acerb
    0.65
     echoes
    0.65
    ãĥķãĤ©
    0.65
    Activations Density 0.618%

    No Known Activations