© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18918
    Prev
    Next
    INDEX
    Explanations

    words related to legal and criminal activities, such as "charge" and "charged"

    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
    686
    +0.10
    0.4%
    314
    +0.10
    0.4%
    195
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.10
    0.03
    686
    +0.10
    0.02
    268
    +0.09
    0.02
    Negative Logits
    angular
    -0.65
     livest
    -0.64
     obser
    -0.64
     Remastered
    -0.64
     illusion
    -0.63
     Orth
    -0.63
    ophe
    -0.62
    VIS
    -0.62
    patch
    -0.61
    atters
    -0.61
    POSITIVE LOGITS
    heet
    1.24
     criminally
    1.09
    llah
    1.01
     charges
    0.90
     indicted
    0.83
     indict
    0.83
    illo
    0.82
     indictment
    0.76
     accused
    0.74
     perjury
    0.74
    Activations Density 0.029%

    No Known Activations