© 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. 26812
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and their actions

    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
    679
    +0.17
    0.8%
    756
    +0.15
    0.7%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.17
    0.03
    224
    +0.15
    0.03
    401
    +0.11
    0.02
    Negative Logits
    ITNESS
    -0.80
    OSS
    -0.66
    ALLY
    -0.64
    PDATE
    -0.63
    Wo
    -0.62
    CO
    -0.61
    Prev
    -0.61
     Oo
    -0.61
    INGTON
    -0.61
     Infinite
    -0.61
    POSITIVE LOGITS
    hips
    1.23
    hip
    1.20
    doms
    1.05
    esses
    0.83
    pin
    0.82
    paces
    0.81
    mith
    0.79
     negotiator
    0.77
    cius
    0.76
     hopeful
    0.76
    Activations Density 0.028%

    No Known Activations