© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 12288
    9. 8-RES_FS12288-JB
    11. 10831
    Prev
    Next
    INDEX
    Explanations

    instances related to charitable donations or community support

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    71
    +0.12
    0.5%
    445
    +0.12
    0.5%
    723
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.12
    0.08
    723
    +0.12
    0.07
    445
    +0.11
    0.07
    Negative Logits
     impe
    -0.76
     overpowered
    -0.74
     hardness
    -0.73
     extracted
    -0.73
     penetration
    -0.73
     brute
    -0.72
    dict
    -0.70
     brut
    -0.70
     manip
    -0.69
    anke
    -0.68
    POSITIVE LOGITS
     fundra
    1.49
     fundraiser
    1.43
     fundraising
    1.40
     charity
    1.28
     outreach
    1.25
     Volunteers
    1.19
     charitable
    1.18
     volunteer
    1.17
     nonprofit
    1.15
     charities
    1.15
    Activations Density 1.879%

    No Known Activations