© 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 49152
    9. 8-RES_FS49152-JB
    11. 37460
    Prev
    Next
    INDEX
    Explanations

    references to the term "Real" in various contexts, particularly related to sports or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    642
    +0.13
    0.6%
    152
    +0.11
    0.5%
    493
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.13
    0.02
    152
    +0.11
    0.02
    642
    +0.10
    0.02
    Negative Logits
    xual
    -0.82
    rav
    -0.65
     Sawyer
    -0.63
    URR
    -0.62
    endants
    -0.60
    orst
    -0.60
     Canaver
    -0.59
    âĸĪâĸĪ
    -0.59
    ower
    -0.59
    lectic
    -0.59
    POSITIVE LOGITS
    istically
    1.45
    istic
    1.36
    ignment
    1.23
    tek
    1.19
     Estate
    1.18
     Madrid
    1.15
    ization
    1.12
    izing
    1.11
    isation
    1.08
    idad
    1.07
    Activations Density 0.008%

    No Known Activations