© 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 3072
    9. 8-RES_FS3072-JB
    11. 155
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships or conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    480
    +0.55
    3.0%
    266
    +0.13
    0.7%
    351
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.55
    0.03
    266
    +0.13
    0.24
    351
    +0.10
    0.09
    Negative Logits
    ourses
    -0.77
    Import
    -0.74
    ilitation
    -0.73
     qualitative
    -0.69
    Recommend
    -0.69
    erred
    -0.68
     organis
    -0.67
    ructure
    -0.67
     conclud
    -0.67
     principally
    -0.66
    POSITIVE LOGITS
     boobs
    1.14
     crap
    1.14
     dudes
    1.12
     shit
    1.11
     dude
    1.10
     poop
    1.08
     dick
    1.05
     jokes
    1.04
     nerds
    1.04
     bitch
    1.03
    Activations Density 7.603%

    No Known Activations