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. 7935
    Prev
    Next
    INDEX
    Explanations

    descriptions of geographical features related to water sources

    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
    288
    +0.12
    0.5%
    240
    +0.10
    0.5%
    537
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.02
    288
    +0.10
    0.02
    617
    +0.10
    0.02
    Negative Logits
     Mutant
    -0.66
    Reloaded
    -0.66
     Horowitz
    -0.64
     Fn
    -0.63
     Files
    -0.62
    iaries
    -0.61
    ictive
    -0.61
     CoC
    -0.60
     verbal
    -0.60
     MFT
    -0.59
    POSITIVE LOGITS
    bank
    1.10
    front
    1.07
    banks
    1.06
     basin
    1.05
     valleys
    1.02
     valley
    1.00
    ine
    0.91
     river
    0.89
     rivers
    0.89
     Nile
    0.89
    Activations Density 0.031%

    No Known Activations