© 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. 26732
    Prev
    Next
    INDEX
    Explanations

    symbols or special characters used in formatting or notation

    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
    447
    +0.17
    0.8%
    314
    +0.11
    0.5%
    480
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.09
    352
    +0.11
    0.09
    321
    +0.11
    0.07
    Negative Logits
     Peb
    -0.83
     scattering
    -0.72
     princ
    -0.72
    omething
    -0.69
     tremend
    -0.67
     Afric
    -0.66
     nearest
    -0.65
     Manhattan
    -0.64
    nown
    -0.64
     dangling
    -0.64
    POSITIVE LOGITS
    º
    1.37
    ¹
    1.24
    į
    1.17
    Į
    1.16
    £
    1.16
    Ĵ
    1.15
    §
    1.14
    ¬
    1.12
    ı
    1.11
    ij
    1.08
    Activations Density 0.154%

    No Known Activations