© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1734
    Prev
    Next
    INDEX
    Explanations

    phrases related to song titles and music awards

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    659
    +0.14
    0.7%
    385
    +0.10
    0.5%
    116
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.08
    128
    +0.10
    0.06
    116
    +0.10
    0.04
    Negative Logits
     ment
    -0.72
    theless
    -0.67
     cannabin
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     destro
    -0.61
    wagen
    -0.59
    nesota
    -0.58
    ãĥĨãĤ£
    -0.58
    ption
    -0.57
     thor
    -0.57
    POSITIVE LOGITS
    ARGET
    1.41
    ribute
    1.37
    olerance
    1.30
    ributes
    1.27
    empt
    1.24
    rench
    1.23
    URN
    1.23
    ractor
    1.20
    akedown
    1.19
    rav
    1.19
    Activations Density 0.079%

    No Known Activations