© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1966
    Prev
    Next
    INDEX
    Explanations

    references to media and entertainment industry

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    459
    +0.16
    0.8%
    165
    +0.10
    0.5%
    97
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.16
    0.06
    570
    +0.10
    0.01
    526
    +0.10
    -0.02
    Negative Logits
    etheless
    -0.94
    ãĤ´ãĥ³
    -0.79
    surprisingly
    -0.65
     respectively
    -0.64
    anwhile
    -0.61
    arthed
    -0.59
    byss
    -0.59
    ¥ŀ
    -0.58
    Accessory
    -0.57
     Annotations
    -0.56
    POSITIVE LOGITS
     â̦"
    1.52
    .")
    1.48
     ..."
    1.48
    ,'"
    1.39
    )"
    1.33
    ,"
    1.32
    ),"
    1.28
    %"
    1.23
    )",
    1.22
    "—
    1.22
    Activations Density 1.446%

    No Known Activations