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 1536
    5. 8-RES_FS1536-JB
    6. 293
    Prev
    Next
    INDEX
    Explanations

    information related to major events or entities, particularly in sports

    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
    45
    +0.12
    0.5%
    657
    +0.10
    0.4%
    661
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.12
    0.07
    288
    +0.10
    0.11
    45
    +0.09
    0.05
    Negative Logits
    adr
    -0.89
    atu
    -0.79
    mates
    -0.78
    creen
    -0.75
    mate
    -0.74
    yer
    -0.74
    rays
    -0.73
    chers
    -0.73
    speak
    -0.71
    elf
    -0.69
    POSITIVE LOGITS
    itarian
    1.09
     depressive
    1.07
     understatement
    1.02
    itized
    0.90
     deterioration
    0.85
    ities
    0.83
     underest
    0.82
     alteration
    0.81
    ity
    0.80
     revisions
    0.79
    Activations Density 2.120%

    No Known Activations