© 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. 7764
    Prev
    Next
    INDEX
    Explanations

    phrases related to civil unrest or societal issues of injustice

    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
    373
    +0.17
    0.8%
    261
    +0.16
    0.7%
    422
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    261
    +0.17
    0.03
    422
    +0.16
    0.02
    371
    +0.11
    0.02
    Negative Logits
    oka
    -0.69
    0000000000000000
    -0.68
    acles
    -0.66
    utenberg
    -0.63
    Password
    -0.62
    ropri
    -0.62
    resy
    -0.61
    Enlarge
    -0.61
    arten
    -0.59
    ially
    -0.59
    POSITIVE LOGITS
    grown
    0.79
    country
    0.79
    drive
    0.74
     again
    0.73
    iflower
    0.73
    lake
    0.72
    roads
    0.72
    sites
    0.71
    reach
    0.69
     town
    0.69
    Activations Density 0.023%

    No Known Activations