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. 770
    Prev
    Next
    INDEX
    Explanations

    descriptions related to criminal activities and various objects or products

    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
    678
    +0.15
    0.7%
    420
    +0.15
    0.7%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.15
    0.18
    289
    +0.15
    0.03
    326
    +0.11
    0.18
    Negative Logits
    Politics
    -0.97
    arcity
    -0.93
    ivals
    -0.89
    Financial
    -0.89
    Daily
    -0.87
    Economic
    -0.86
    Services
    -0.84
    humans
    -0.80
    Events
    -0.79
    Money
    -0.78
    POSITIVE LOGITS
     protr
    1.73
     diameter
    1.69
     thickness
    1.65
     curved
    1.44
     molded
    1.42
     width
    1.40
     thicker
    1.38
     translucent
    1.36
     rectangular
    1.35
     angled
    1.34
    Activations Density 4.801%

    No Known Activations