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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13733
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and positivity, including food descriptions and musical enjoyment

    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
    68
    +0.10
    0.4%
    195
    +0.10
    0.4%
    480
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.10
    0.15
    352
    +0.10
    0.15
    321
    +0.09
    0.12
    Negative Logits
     Libyan
    -0.71
     Tunis
    -0.70
     Counsel
    -0.70
     retreat
    -0.67
     scatter
    -0.66
     Eisen
    -0.64
     Communications
    -0.64
     lodging
    -0.63
     memorandum
    -0.63
     Ukrain
    -0.62
    POSITIVE LOGITS
    º
    1.14
    ¡
    1.13
    ¬
    1.13
    ¹
    1.11
    į
    1.09
    ½
    1.09
    ı
    1.04
    Ĵ
    1.03
    »
    1.01
    £
    0.99
    Activations Density 0.412%

    No Known Activations