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. 799
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to relationships and contracts

    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
    171
    +0.13
    0.6%
    264
    +0.13
    0.6%
    74
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.13
    0.09
    264
    +0.13
    0.05
    205
    +0.12
    0.07
    Negative Logits
    Īè
    -0.68
     sugg
    -0.59
    Incre
    -0.52
    iche
    -0.51
    xtap
    -0.51
     foregoing
    -0.51
    Previously
    -0.51
    Pur
    -0.50
    ============
    -0.49
    ĵĺ
    -0.49
    POSITIVE LOGITS
    foundland
    0.77
    selves
    0.71
    ohm
    0.69
    ween
    0.69
    llor
    0.63
    luaj
    0.61
    undy
    0.59
    etheless
    0.59
    ,,,,
    0.59
    rite
    0.58
    Activations Density 3.442%

    No Known Activations