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. 11129
    Prev
    Next
    INDEX
    Explanations

    references to sports and related events

    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
    314
    +0.17
    0.8%
    169
    +0.12
    0.5%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.06
    169
    +0.12
    0.05
    334
    +0.11
    0.04
    Negative Logits
     routine
    -0.73
     tune
    -0.73
     convincing
    -0.72
     offence
    -0.70
     wheelchair
    -0.70
     bulk
    -0.69
     weakest
    -0.69
     brunt
    -0.66
     offense
    -0.65
     sentence
    -0.65
    POSITIVE LOGITS
     Digest
    1.17
     Matters
    1.13
    pedia
    1.11
    Info
    1.06
     Analytics
    1.05
    Week
    1.03
    Ins
    1.02
     Magazine
    1.00
    Fix
    1.00
    News
    0.99
    Activations Density 0.279%

    No Known Activations