© 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. 8860
    Prev
    Next
    INDEX
    Explanations

    information related to crime and criminal activities

    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
    362
    +0.13
    0.6%
    268
    +0.09
    0.4%
    291
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.06
    608
    +0.09
    0.05
    16
    +0.09
    0.04
    Negative Logits
    Opt
    -0.76
    Cath
    -0.74
    Tokens
    -0.73
    itar
    -0.68
     optim
    -0.67
    Tool
    -0.67
     pessim
    -0.67
    ä¸Ĭ
    -0.66
    Publisher
    -0.66
     pag
    -0.65
    POSITIVE LOGITS
     crimes
    1.19
     murder
    1.14
     felony
    1.09
     kidnapping
    1.08
     offences
    1.08
     wrongful
    1.06
     alleged
    1.05
     Crimes
    1.04
     murders
    1.04
     indict
    1.04
    Activations Density 0.207%

    No Known Activations