© 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. 11886
    Prev
    Next
    INDEX
    Explanations

    the word "so" indicating a logical conclusion or continuation in a sentence

    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
    468
    +0.11
    0.5%
    214
    +0.10
    0.4%
    240
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.11
    0.02
    240
    +0.10
    0.02
    214
    +0.10
    0.02
    Negative Logits
     Cree
    -0.67
     Neigh
    -0.64
    ropolitan
    -0.60
     Kids
    -0.59
     burg
    -0.59
     Dre
    -0.58
    WN
    -0.58
    gie
    -0.57
     Tact
    -0.57
     Milan
    -0.57
    POSITIVE LOGITS
     forth
    1.45
    forth
    1.08
    bered
    1.03
    othe
    1.01
    oths
    0.98
    apy
    0.97
    ooo
    0.88
    oooo
    0.86
    oner
    0.83
     far
    0.81
    Activations Density 0.026%

    No Known Activations