© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    phrases related to skepticism and questioning in conversation

    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
    750
    +0.11
    0.5%
    509
    +0.11
    0.5%
    306
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    702
    +0.11
    0.02
    374
    +0.11
    0.01
    287
    +0.10
    0.02
    Negative Logits
    ribut
    -0.57
    stroke
    -0.56
    aples
    -0.55
     nucleus
    -0.55
    irus
    -0.55
    CTV
    -0.54
    ixels
    -0.54
    Mobil
    -0.54
    ixel
    -0.54
    adeon
    -0.53
    POSITIVE LOGITS
     heck
    0.96
     hell
    0.95
     fuck
    0.89
    ?!
    0.83
     HELL
    0.81
    ?)
    0.81
     Fuck
    0.80
    ...?
    0.80
    !?
    0.79
    quished
    0.77
    Activations Density 0.080%

    No Known Activations