© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9551
    Prev
    Next
    INDEX
    Explanations

    references to specific events or notable individuals in different contexts

    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
    480
    +0.52
    2.8%
    447
    +0.21
    1.1%
    373
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.01
    266
    +0.21
    0.09
    346
    +0.15
    0.05
    Negative Logits
     meantime
    -0.67
     tomorrow
    -0.65
     behav
    -0.59
     meanwhile
    -0.58
     depends
    -0.58
    anwhile
    -0.58
    onday
    -0.56
     wont
    -0.56
     Amen
    -0.55
     accordingly
    -0.55
    POSITIVE LOGITS
    ixty
    0.61
    FTWARE
    0.57
    schild
    0.56
     unexpectedly
    0.55
     mysteriously
    0.51
    Reviewer
    0.51
    itled
    0.49
     abruptly
    0.49
     announcing
    0.48
     keynote
    0.47
    Activations Density 1.106%

    No Known Activations