© 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. 9162
    Prev
    Next
    INDEX
    Explanations

    phrases related to charitable activities or political initiatives aimed at making a difference

    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
    496
    +0.14
    0.6%
    241
    +0.13
    0.6%
    314
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.04
    314
    +0.13
    0.01
    496
    +0.13
    0.04
    Negative Logits
     constitu
    -0.78
     exha
    -0.74
    opausal
    -0.71
     discharge
    -0.69
     nerv
    -0.68
     reg
    -0.66
     discovery
    -0.66
     repetition
    -0.65
     flush
    -0.65
     occas
    -0.64
    POSITIVE LOGITS
    away
    1.12
    ings
    0.99
     Your
    0.96
    aways
    0.96
     Yourself
    0.94
     Away
    0.94
    ers
    0.92
    Maker
    0.87
    ership
    0.86
    Your
    0.86
    Activations Density 0.164%

    No Known Activations