© 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 49152
    9. 8-RES_FS49152-JB
    11. 25775
    Prev
    Next
    INDEX
    Explanations

    words related to separation and division

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    7
    +0.12
    0.5%
    587
    +0.09
    0.4%
    506
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    539
    +0.12
    0.01
    702
    +0.09
    0.01
    503
    +0.09
    0.00
    Negative Logits
     Springer
    -0.72
    CHR
    -0.69
     Kush
    -0.61
     Hemp
    -0.61
     Gone
    -0.59
     HIP
    -0.59
     Gillespie
    -0.58
    mop
    -0.58
     mercy
    -0.56
    ORN
    -0.56
    POSITIVE LOGITS
    al
    1.18
    alities
    1.17
    uously
    1.10
    alis
    1.09
    uous
    1.06
    ance
    1.06
    ances
    1.03
    alist
    1.02
    ateur
    1.00
    iple
    1.00
    Activations Density 0.009%

    No Known Activations