© 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. 1336
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and political discussions, especially related to immigration and citizenship

    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
    640
    +0.19
    0.9%
    373
    +0.18
    0.9%
    442
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.04
    6
    +0.18
    0.04
    160
    +0.13
    0.04
    Negative Logits
     stray
    -0.80
     administr
    -0.79
     territ
    -0.78
     repatri
    -0.75
     payday
    -0.75
     synerg
    -0.73
     diving
    -0.73
     timely
    -0.73
     wiser
    -0.71
     downstream
    -0.71
    POSITIVE LOGITS
    Narr
    1.38
    SOURCE
    1.17
    Interview
    1.11
    Anyway
    1.10
    LES
    1.06
    Leary
    1.05
    Original
    1.05
    Instruct
    1.05
    ((
    1.04
    Reward
    1.03
    Activations Density 0.077%

    No Known Activations