© 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. 7678
    Prev
    Next
    INDEX
    Explanations

    terms related to the death penalty, including words like "unconstitutional," "executions," "death row," and specific forms of execution

    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
    728
    +0.13
    0.6%
    628
    +0.10
    0.5%
    556
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.13
    0.03
    628
    +0.10
    0.02
    288
    +0.10
    0.03
    Negative Logits
    é¾įåĸļ士
    -0.81
     Clouds
    -0.79
    arity
    -0.79
    Remote
    -0.76
    Cloud
    -0.71
    sonian
    -0.70
    bits
    -0.70
    Beer
    -0.69
    CRE
    -0.68
    Ocean
    -0.68
    POSITIVE LOGITS
     inmate
    1.15
     abolition
    1.09
     inmates
    1.06
     incarcer
    1.06
     convict
    1.04
     incarcerated
    0.95
     parole
    0.93
     prisoners
    0.92
     sentences
    0.92
     murder
    0.92
    Activations Density 0.083%

    No Known Activations