Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11573
    Prev
    Next
    INDEX
    Explanations

    information regarding legal processes and regulations

    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
    739
    +0.10
    0.4%
    26
    +0.10
    0.4%
    605
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.10
    0.02
    409
    +0.10
    0.02
    210
    +0.10
    0.02
    Negative Logits
    Ĥª
    -0.80
    rift
    -0.79
    Shield
    -0.77
    slave
    -0.74
    alian
    -0.74
    OY
    -0.71
    Bench
    -0.68
    Community
    -0.68
    cloud
    -0.67
    asonic
    -0.67
    POSITIVE LOGITS
     receipt
    1.16
     arrival
    1.10
     inception
    1.07
     completion
    1.03
     onset
    1.00
     encountering
    0.99
     arriving
    0.99
     receiving
    0.95
     initiating
    0.94
     enactment
    0.91
    Activations Density 0.092%

    No Known Activations