© 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 24576
    9. 8-RES_FS24576-JB
    11. 1288
    Prev
    Next
    INDEX
    Explanations

    specific references to certain objects or locations within longer passages of text

    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
    481
    +0.19
    0.9%
    393
    +0.18
    0.9%
    362
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.09
    636
    +0.18
    0.07
    393
    +0.12
    0.07
    Negative Logits
    ornings
    -0.78
    wark
    -0.75
    ä¸ī
    -0.74
    HH
    -0.71
    swing
    -0.71
    Scotland
    -0.69
    ichick
    -0.68
    shine
    -0.68
    Mania
    -0.67
    ategory
    -0.67
    POSITIVE LOGITS
     entire
    1.58
     remainder
    1.43
     entirety
    1.36
     contents
    1.33
     offending
    1.30
     remaining
    1.23
     same
    1.23
     slightest
    1.21
     requisite
    1.21
     whole
    1.21
    Activations Density 0.401%

    No Known Activations