© 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. 45751
    Prev
    Next
    INDEX
    Explanations

    mentions of hydration and related concepts

    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
    288
    +0.12
    0.5%
    67
    +0.12
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.01
    149
    +0.12
    0.01
    441
    +0.10
    0.01
    Negative Logits
    ãģį
    -0.86
    */(
    -0.78
    éĹĺ
    -0.68
     Borough
    -0.68
    istically
    -0.66
    ãģĦ
    -0.63
     Finder
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.63
     Canary
    -0.63
     sender
    -0.62
    POSITIVE LOGITS
    ration
    1.25
    rolog
    1.23
    rox
    1.18
    rol
    1.17
    rogen
    1.16
    rop
    1.12
    roph
    1.11
    rated
    1.04
    roc
    1.04
    rant
    1.02
    Activations Density 0.004%

    No Known Activations