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. 21673
    Prev
    Next
    INDEX
    Explanations

    economic and social implications related to development and growth

    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
    380
    +0.12
    0.5%
    447
    +0.12
    0.5%
    368
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.12
    0.05
    724
    +0.12
    0.06
    147
    +0.11
    0.05
    Negative Logits
    sonian
    -0.73
    actory
    -0.69
    irgin
    -0.64
    nant
    -0.64
     Vide
    -0.62
    acket
    -0.62
     Founding
    -0.61
    enary
    -0.60
    dream
    -0.59
    purpose
    -0.59
    POSITIVE LOGITS
     plummeted
    1.27
     skyrocket
    1.24
     soared
    1.20
     plummet
    1.10
     soar
    1.09
     surged
    1.05
     fluct
    1.04
     deteriorated
    1.02
     slump
    1.01
     rose
    0.99
    Activations Density 0.301%

    No Known Activations