© 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. 8046
    Prev
    Next
    INDEX
    Explanations

    specific grades or educational levels

    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
    71
    +0.13
    0.6%
    376
    +0.11
    0.5%
    174
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.13
    0.02
    80
    +0.11
    0.02
    508
    +0.10
    0.02
    Negative Logits
    eers
    -0.74
     quo
    -0.70
    ĸļ
    -0.70
     writ
    -0.66
     shortened
    -0.65
     Sands
    -0.62
     Lei
    -0.62
     Ruins
    -0.62
     Mith
    -0.60
     Stout
    -0.59
    POSITIVE LOGITS
    iffin
    1.24
    anny
    1.20
    udge
    1.20
    umpy
    1.20
    ains
    1.16
    ayson
    1.10
    iff
    1.10
    illed
    1.09
    illing
    1.07
    aced
    1.06
    Activations Density 0.014%

    No Known Activations