© 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 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. 8942
    Prev
    Next
    INDEX
    Explanations

    phrases related to the absence of something

    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
    609
    +0.11
    0.5%
    669
    +0.10
    0.5%
    257
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.11
    0.04
    669
    +0.10
    0.03
    455
    +0.10
    0.03
    Negative Logits
    raq
    -0.87
    mun
    -0.82
    geist
    -0.78
    iers
    -0.74
    cow
    -0.72
    late
    -0.72
    soon
    -0.66
    lish
    -0.65
    ard
    -0.65
    stru
    -0.65
    POSITIVE LOGITS
     sacrificing
    1.22
     relying
    1.14
     risking
    1.09
     necessarily
    1.08
     compromising
    1.06
     requiring
    1.03
     needing
    1.01
     knowing
    0.99
     mentioning
    0.98
     regard
    0.97
    Activations Density 0.035%

    No Known Activations