© 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. 10664
    Prev
    Next
    INDEX
    Explanations

    proper nouns and brand names

    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
    479
    +0.11
    0.5%
    481
    +0.10
    0.5%
    722
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.11
    0.04
    585
    +0.10
    0.04
    146
    +0.09
    0.04
    Negative Logits
    rongh
    -0.88
    vati
    -0.85
    vag
    -0.82
    multipl
    -0.81
    rab
    -0.80
    nec
    -0.79
    uggest
    -0.79
    redd
    -0.79
    adal
    -0.76
    requ
    -0.75
    POSITIVE LOGITS
     Industries
    1.31
     Enterprises
    1.28
     Productions
    1.28
     Studios
    1.24
     Networks
    1.20
     Publications
    1.16
     Analytics
    1.16
     Publishing
    1.15
     Communications
    1.15
     Investments
    1.15
    Activations Density 0.171%

    No Known Activations