© 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. 1675
    Prev
    Next
    INDEX
    Explanations

    political and international relations concepts

    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
    522
    +0.10
    0.5%
    483
    +0.10
    0.5%
    464
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    697
    +0.10
    0.03
    702
    +0.10
    0.04
    522
    +0.10
    0.03
    Negative Logits
    earable
    -0.59
    venants
    -0.58
    EVA
    -0.54
    ablished
    -0.53
     guiName
    -0.52
    ritional
    -0.52
    ptin
    -0.51
    Blocks
    -0.51
    qqa
    -0.50
     Skydragon
    -0.50
    POSITIVE LOGITS
    )</
    1.06
    )}
    1.03
    *)
    0.99
    -)
    0.95
     paraph
    0.95
    !)
    0.91
    ?)
    0.88
    )
    0.87
    )—
    0.86
    âĢ¦)
    0.85
    Activations Density 0.452%

    No Known Activations