© 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 24576
    9. 8-RES_FS24576-JB
    11. 11856
    Prev
    Next
    INDEX
    Explanations

    names or words containing 'Ol'

    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
    35
    +0.14
    0.6%
    296
    +0.11
    0.5%
    240
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.14
    0.02
    188
    +0.11
    0.01
    487
    +0.10
    0.01
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.77
    liness
    -0.74
    eering
    -0.74
    ت
    -0.72
    -+-+
    -0.66
     اÙĦ
    -0.66
     pitted
    -0.66
    åij
    -0.65
     IEEE
    -0.64
    plane
    -0.64
    POSITIVE LOGITS
    iver
    0.96
    sen
    0.96
    mbuds
    0.92
    ga
    0.90
    atile
    0.88
    mer
    0.87
    ibrary
    0.84
    untary
    0.83
    sin
    0.82
    ipop
    0.82
    Activations Density 0.017%

    No Known Activations