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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19328
    Prev
    Next
    INDEX
    Explanations

    expressions of empathy or sharing announcements

    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
    665
    +0.14
    0.6%
    680
    +0.11
    0.5%
    498
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.06
    498
    +0.11
    0.05
    641
    +0.10
    0.04
    Negative Logits
     mishand
    -0.61
    sbm
    -0.61
     mist
    -0.61
     clashed
    -0.60
     Vog
    -0.59
     outnumbered
    -0.59
     Leh
    -0.59
     Created
    -0.59
     hull
    -0.58
    alties
    -0.57
    POSITIVE LOGITS
     myself
    1.09
     congratulations
    0.86
     disclaimer
    0.84
    thank
    0.81
     ourselves
    0.79
     THANK
    0.79
     ASAP
    0.79
    :]
    0.78
     tonight
    0.78
     my
    0.77
    Activations Density 0.245%

    No Known Activations