© 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. 8191
    Prev
    Next
    INDEX
    Explanations

    phrases related to the level of care and effort put into something, as well as mentions of competition and damage

    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
    444
    +0.12
    0.5%
    684
    +0.09
    0.4%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.12
    0.06
    724
    +0.09
    0.07
    288
    +0.09
    0.07
    Negative Logits
    iland
    -0.75
    ilet
    -0.72
    é¾
    -0.67
    vernight
    -0.67
    ãĤ´ãĥ³
    -0.65
    cffffcc
    -0.62
    uces
    -0.62
    REL
    -0.62
    ilaterally
    -0.61
    dry
    -0.60
    POSITIVE LOGITS
     afforded
    0.93
     they
    0.89
     wrought
    0.86
     inherent
    0.80
     bestowed
    0.80
     she
    0.75
     he
    0.74
    antry
    0.73
     involved
    0.72
     emanating
    0.70
    Activations Density 0.373%

    No Known Activations