© 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. 22120
    Prev
    Next
    INDEX
    Explanations

    phrases related to introspection or self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered 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
    36
    +0.14
    0.7%
    512
    +0.13
    0.6%
    221
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.14
    0.04
    512
    +0.13
    0.03
    704
    +0.11
    0.02
    Negative Logits
    aris
    -0.76
    eto
    -0.76
    loads
    -0.76
    ioxide
    -0.75
    ourse
    -0.74
    ORTS
    -0.73
    mins
    -0.72
    ourses
    -0.72
    otte
    -0.72
    CTV
    -0.72
    POSITIVE LOGITS
     deterrent
    1.03
     headache
    1.01
     contradiction
    0.96
     nuisance
    0.96
     rarity
    0.93
     tease
    0.91
     coincidence
    0.91
     joke
    0.91
     novelty
    0.88
     stretch
    0.85
    Activations Density 0.070%

    No Known Activations