© 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 EvalsExportsinterp-engineNEWAPI 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. 4359
    Prev
    Next
    INDEX
    Explanations

    words related to legal issues or terms associated with discrimination or offensive language

    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
    481
    +0.13
    0.6%
    713
    +0.11
    0.5%
    408
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    713
    +0.13
    0.04
    329
    +0.11
    0.04
    408
    +0.10
    0.05
    Negative Logits
    ĸļ
    -0.94
    emis
    -0.83
    oleon
    -0.81
    mediate
    -0.79
    united
    -0.78
    wright
    -0.76
    arest
    -0.76
    aintain
    -0.74
    confirmed
    -0.73
    hm
    -0.72
    POSITIVE LOGITS
     behavior
    1.23
     behaviour
    1.21
     tendencies
    1.11
     behaviors
    1.09
     behaviours
    1.04
     remarks
    1.00
     impulses
    0.99
     actions
    0.97
     statements
    0.96
     remark
    0.96
    Activations Density 0.177%

    No Known Activations