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 6144
    5. 8-RES_FS6144-JB
    6. 5337
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and installation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    293
    +0.10
    0.4%
    409
    +0.10
    0.4%
    399
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.08
    172
    +0.10
    0.07
    300
    +0.10
    0.09
    Negative Logits
     yesterday
    -0.76
    eret
    -0.72
     today
    -0.67
     Tuesday
    -0.65
    prov
    -0.64
     Wednesday
    -0.63
     Thursday
    -0.63
     tonight
    -0.61
     prov
    -0.60
     beforehand
    -0.60
    POSITIVE LOGITS
     realize
    0.96
     finally
    0.96
     realise
    0.92
    iphany
    0.92
     realized
    0.89
     ceases
    0.87
     matured
    0.87
     exhaustion
    0.86
    apsed
    0.86
     maturity
    0.85
    Activations Density 1.741%

    No Known Activations