© 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. 45755
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to retaliation and its consequences

    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
    763
    +0.12
    0.6%
    259
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.12
    0.01
    140
    +0.11
    0.01
    763
    +0.11
    0.01
    Negative Logits
    ographics
    -0.77
    orage
    -0.74
     livest
    -0.74
     ç¥ŀ
    -0.73
    ODE
    -0.70
    olesterol
    -0.70
    leaf
    -0.68
    opathy
    -0.65
    scape
    -0.65
    oak
    -0.64
    POSITIVE LOGITS
     retali
    1.28
     retaliation
    1.25
     retaliate
    1.24
     against
    1.15
     retribution
    1.01
     repr
    1.00
     wrath
    0.98
     attacks
    0.94
    against
    0.92
     harshly
    0.92
    Activations Density 0.017%

    No Known Activations