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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1563
    Prev
    Next
    INDEX
    Explanations

    the phrase "going to," especially when followed by another verb

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    665
    +0.12
    0.6%
    2
    +0.11
    0.5%
    551
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.08
    139
    +0.11
    0.07
    551
    +0.09
    0.07
    Negative Logits
    CTV
    -0.80
    cius
    -0.72
    Reporting
    -0.71
    Pres
    -0.70
    amps
    -0.68
    checking
    -0.68
    quickShipAvailable
    -0.65
    mere
    -0.64
     Provided
    -0.61
    VIDEO
    -0.61
    POSITIVE LOGITS
     be
    1.28
     lose
    1.06
     continue
    1.02
     stick
    0.98
     get
    0.98
     make
    0.97
     succeed
    0.96
     regress
    0.95
     give
    0.95
     survive
    0.94
    Activations Density 0.549%

    No Known Activations