© 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 1536
    9. 8-RES_FS1536-JB
    11. 1171
    Prev
    Next
    INDEX
    Explanations

    organizations and investigative actions or procedures related to news or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.15
    0.7%
    677
    +0.11
    0.5%
    232
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.10
    314
    +0.11
    0.00
    696
    +0.10
    0.10
    Negative Logits
     slowing
    -0.68
     vain
    -0.67
     suppressed
    -0.66
     quo
    -0.65
     dece
    -0.65
    etheless
    -0.64
     demolition
    -0.63
     diver
    -0.63
     downhill
    -0.63
     intuitive
    -0.61
    POSITIVE LOGITS
    oran
    0.95
    chin
    0.91
    atson
    0.85
    edes
    0.84
    vent
    0.82
    itialized
    0.82
    icia
    0.81
    alys
    0.81
    mans
    0.80
    omer
    0.79
    Activations Density 1.959%

    No Known Activations