© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45805
    Prev
    Next
    INDEX
    Explanations

    references to specific product models or names, particularly in technology

    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
    211
    +0.14
    0.7%
    300
    +0.11
    0.5%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.14
    0.01
    365
    +0.11
    0.01
    676
    +0.10
    0.01
    Negative Logits
     Emin
    -0.73
    ĨĴ
    -0.72
    ï¸
    -0.66
    女
    -0.65
    isance
    -0.65
     Dortmund
    -0.64
    éĹĺ
    -0.63
    IGH
    -0.63
    llor
    -0.62
     Galile
    -0.62
    POSITIVE LOGITS
    bed
    1.22
    oola
    1.08
    ula
    1.07
    riz
    1.06
    ular
    1.06
    atha
    1.05
    ulated
    1.02
    bing
    1.02
    ril
    1.00
    acco
    0.98
    Activations Density 0.007%

    No Known Activations