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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1235
    Prev
    Next
    INDEX
    Explanations

    economic and social class references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    600
    +0.10
    0.4%
    420
    +0.10
    0.4%
    111
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.14
    600
    +0.10
    0.07
    669
    +0.09
    0.09
    Negative Logits
    inventoryQuantity
    -0.76
    ĸļ
    -0.73
    wcsstore
    -0.71
     Protocol
    -0.70
    urgy
    -0.68
    agate
    -0.67
    Closure
    -0.67
    atography
    -0.66
    otide
    -0.64
    urgical
    -0.64
    POSITIVE LOGITS
     individuals
    1.58
     citizens
    1.45
     persons
    1.44
     youths
    1.39
     youngsters
    1.35
     people
    1.34
     residents
    1.31
     men
    1.28
     participants
    1.28
     members
    1.27
    Activations Density 4.319%

    No Known Activations