© 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. 7458
    Prev
    Next
    INDEX
    Explanations

    financial terms and corporate news

    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
    288
    +0.14
    0.7%
    415
    +0.12
    0.6%
    283
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.14
    0.01
    288
    +0.12
    0.01
    326
    +0.10
    0.01
    Negative Logits
     fats
    -0.69
    ÃĽ
    -0.67
     neurolog
    -0.60
     symmetry
    -0.60
    Second
    -0.60
    obbies
    -0.59
     nutrit
    -0.59
     corros
    -0.59
     beet
    -0.58
    metics
    -0.58
    POSITIVE LOGITS
    acle
    1.30
    atively
    1.29
    pole
    1.26
     encamp
    1.05
    acular
    1.02
    acles
    0.97
     tents
    0.86
    cloth
    0.85
     tent
    0.84
     flap
    0.82
    Activations Density 0.024%

    No Known Activations