© 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. 19391
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and software development

    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
    235
    +0.11
    0.5%
    502
    +0.11
    0.5%
    180
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.06
    502
    +0.11
    0.04
    299
    +0.10
    0.04
    Negative Logits
    lain
    -0.84
    spin
    -0.80
    theless
    -0.70
    */(
    -0.68
    size
    -0.66
    mort
    -0.65
    rooms
    -0.65
    look
    -0.64
    drawn
    -0.63
    ividual
    -0.63
    POSITIVE LOGITS
    Äĩ
    1.53
    ya
    1.31
    ère
    1.31
    emi
    1.17
    yah
    1.14
    kson
    1.11
    ño
    1.05
    Äį
    1.02
    orno
    1.01
    oglu
    0.99
    Activations Density 0.120%

    No Known Activations