© 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. 18815
    Prev
    Next
    INDEX
    Explanations

    locations or events in this case, the neuron seems to be focused on events happening in different regions across the globe

    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
    87
    +0.22
    1.1%
    470
    +0.10
    0.5%
    620
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.22
    0.06
    308
    +0.10
    0.04
    475
    +0.10
    0.05
    Negative Logits
    inventoryQuantity
    -0.66
     hiber
    -0.64
     awa
    -0.61
     idle
    -0.60
     silence
    -0.59
     seiz
    -0.58
     reconnect
    -0.58
    oooooooooooooooo
    -0.57
    ccording
    -0.56
    à¨
    -0.56
    POSITIVE LOGITS
     Ltd
    0.91
     LLP
    0.87
     (@
    0.81
     guiActiveUnfocused
    0.80
     LLC
    0.74
     Edition
    0.73
     fame
    0.73
    orum
    0.72
     Architects
    0.69
     ].
    0.68
    Activations Density 0.487%

    No Known Activations