© 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 3072
    5. 8-RES_FS3072-JB
    6. 217
    Prev
    Next
    INDEX
    Explanations

    the word "quite" used in a context indicating a high degree or level of something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    760
    +0.10
    0.4%
    438
    +0.09
    0.4%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    760
    +0.10
    0.04
    438
    +0.09
    0.04
    331
    +0.09
    0.03
    Negative Logits
    elsen
    -0.84
     DRAG
    -0.81
    venant
    -0.77
    ulkan
    -0.77
    ULTS
    -0.75
    ults
    -0.73
    orer
    -0.69
    erson
    -0.67
    adium
    -0.66
    olan
    -0.65
    POSITIVE LOGITS
     frankly
    0.96
     alright
    0.75
     literally
    0.71
     nice
    0.68
     nifty
    0.68
    \\\\
    0.67
     spoil
    0.67
     tame
    0.66
    entimes
    0.66
    anism
    0.64
    Activations Density 0.242%

    No Known Activations