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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23886
    Prev
    Next
    INDEX
    Explanations

    scientific data related to environmental impact, specifically greenhouse gases and their effects

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.16
    0.8%
    447
    +0.13
    0.6%
    135
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.07
    6
    +0.13
    0.06
    764
    +0.12
    0.04
    Negative Logits
     counselors
    -0.76
    idays
    -0.70
     preempt
    -0.68
     answ
    -0.66
     veter
    -0.65
     boycot
    -0.65
     punish
    -0.64
     quotas
    -0.64
     specials
    -0.64
     slut
    -0.63
    POSITIVE LOGITS
     Photograph
    1.19
     Wikimedia
    1.18
     Courtesy
    1.15
    Courtesy
    1.13
    Phot
    1.12
     Illust
    1.09
     Image
    1.08
    phot
    1.07
     Flickr
    1.06
    photo
    1.01
    Activations Density 0.263%

    No Known Activations