© 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. 22010
    Prev
    Next
    INDEX
    Explanations

    numeric figures following a forward slash, possibly related to dates or references

    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
    641
    +0.13
    0.6%
    175
    +0.10
    0.4%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.13
    0.02
    175
    +0.10
    0.02
    350
    +0.09
    0.02
    Negative Logits
     Dragonbound
    -0.69
     blush
    -0.67
     Syl
    -0.64
     Opportun
    -0.63
    antha
    -0.63
     lettuce
    -0.60
     tailor
    -0.58
     temper
    -0.58
     short
    -0.57
     sul
    -0.57
    POSITIVE LOGITS
    11
    1.06
    oct
    0.91
    12
    0.91
    13
    0.90
    2012
    0.89
    ¶
    0.87
    911
    0.86
    10
    0.86
    9
    0.83
    2013
    0.83
    Activations Density 0.020%

    No Known Activations