Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41369
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or criticism towards various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    497
    +0.13
    0.6%
    111
    +0.11
    0.5%
    147
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.03
    147
    +0.11
    0.02
    241
    +0.10
    0.02
    Negative Logits
     moder
    -0.72
     thumbs
    -0.68
     interf
    -0.67
    odan
    -0.66
     tolerance
    -0.65
     scanner
    -0.62
     antiv
    -0.61
     scales
    -0.61
     thumb
    -0.60
     numerical
    -0.60
    POSITIVE LOGITS
    2016
    1.16
    2017
    1.15
    2014
    1.10
    2018
    1.09
    2020
    1.07
    2011
    1.06
    2012
    1.06
    2015
    1.04
    2013
    1.03
    2010
    1.00
    Activations Density 0.016%

    No Known Activations