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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11960
    Prev
    Next
    INDEX
    Explanations

    monetary values in different currencies

    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
    685
    +0.12
    0.5%
    110
    +0.10
    0.4%
    319
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    685
    +0.12
    0.02
    319
    +0.10
    0.02
    352
    +0.09
    0.03
    Negative Logits
    cknow
    -0.69
     McH
    -0.67
    istical
    -0.65
    blogs
    -0.65
    opic
    -0.64
     Tinker
    -0.64
    Bir
    -0.63
    sburgh
    -0.63
    HEAD
    -0.63
    ablished
    -0.61
    POSITIVE LOGITS
     (£
    1.56
     ($
    1.53
     apiece
    1.12
    /$
    1.08
    ($
    1.03
     USD
    1.01
     sterling
    1.00
    USD
    0.99
     (~
    0.97
     payable
    0.97
    Activations Density 0.063%

    No Known Activations