© 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. 1961
    Prev
    Next
    INDEX
    Explanations

    words related to emotions and personal experiences

    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
    566
    +0.14
    0.6%
    344
    +0.09
    0.4%
    314
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.04
    696
    +0.09
    0.03
    39
    +0.08
    0.03
    Negative Logits
    osa
    -0.59
    matically
    -0.59
    Subject
    -0.59
    alyses
    -0.58
     airspace
    -0.57
     hostage
    -0.56
    ologically
    -0.56
     negotiator
    -0.55
    irection
    -0.54
     negotiators
    -0.54
    POSITIVE LOGITS
     been
    1.14
     Been
    1.05
    been
    1.00
    gotten
    0.99
    20439
    0.97
     gotten
    0.93
     seen
    0.89
    tta
    0.80
    tten
    0.79
     done
    0.77
    Activations Density 0.027%

    No Known Activations