© 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. 9666
    Prev
    Next
    INDEX
    Explanations

    information related to real estate, housing issues, and property management

    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
    +0.28
    1.4%
    447
    +0.18
    0.9%
    481
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.15
    442
    +0.18
    0.14
    160
    +0.17
    0.13
    Negative Logits
     overth
    -0.87
     analys
    -0.84
     treason
    -0.84
     consum
    -0.83
     oath
    -0.83
     assassin
    -0.82
     traitor
    -0.82
     aven
    -0.81
     deliber
    -0.78
     diseng
    -0.78
    POSITIVE LOGITS
    Enlarge
    1.44
    Residents
    1.42
    But
    1.40
    Some
    1.39
    Copyright
    1.38
    Companies
    1.36
    Advertisement
    1.35
    Many
    1.34
    They
    1.33
    Those
    1.32
    Activations Density 0.467%

    No Known Activations