© 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 12288
    5. 8-RES_FS12288-JB
    6. 588
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or objects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    120
    +0.12
    0.6%
    154
    +0.10
    0.5%
    287
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.12
    0.06
    373
    +0.10
    -0.03
    284
    +0.10
    0.06
    Negative Logits
     Shutterstock
    -0.77
    ngth
    -0.76
    dden
    -0.75
    achev
    -0.74
    ĸļ
    -0.72
    orer
    -0.69
    antage
    -0.69
    earch
    -0.69
    yip
    -0.66
    visor
    -0.65
    POSITIVE LOGITS
    é¾įå
    0.78
    rical
    0.76
    ̶
    0.68
    å°Ĩ
    0.63
    é¾įåĸļ士
    0.63
     Exhibition
    0.59
    eor
    0.59
     Railway
    0.59
    swick
    0.58
    ĩ
    0.58
    Activations Density 0.433%

    No Known Activations