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. 151
    Prev
    Next
    INDEX
    Explanations

    words related to bars or establishments where alcoholic beverages are typically served

    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
    370
    +0.13
    0.6%
    314
    +0.12
    0.6%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.13
    232
    +0.12
    0.08
    211
    +0.10
    0.04
    Negative Logits
    lihood
    -0.92
    IBLE
    -0.82
     Instruments
    -0.73
    sie
    -0.72
    ãģį
    -0.69
    ibilities
    -0.69
    ACTED
    -0.68
     CHRIST
    -0.65
    ç«
    -0.65
     UE
    -0.64
    POSITIVE LOGITS
    bara
    1.24
    celona
    1.17
    riers
    1.14
    itone
    1.14
    iatric
    1.14
    bers
    1.13
    bell
    1.10
    bed
    1.09
    becue
    1.07
    bing
    1.03
    Activations Density 2.126%

    No Known Activations