© 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. 12187
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases that convey strong opinions or emotions

    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
    362
    +0.15
    0.7%
    151
    +0.12
    0.6%
    446
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.15
    0.07
    362
    +0.12
    0.07
    446
    +0.12
    0.05
    Negative Logits
    uther
    -0.80
    uph
    -0.79
    urga
    -0.79
    ecause
    -0.79
    Reviewed
    -0.78
    vier
    -0.77
    someone
    -0.75
    utenant
    -0.75
    =-=-=-=-
    -0.75
     Possibly
    -0.75
    POSITIVE LOGITS
     inability
    1.20
     namesake
    1.18
     reputation
    1.14
     penchant
    1.12
     counterparts
    1.12
     fortunes
    1.12
     nature
    1.11
     predecessors
    1.11
     antics
    1.10
     foray
    1.10
    Activations Density 0.269%

    No Known Activations