© 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. 9855
    Prev
    Next
    INDEX
    Explanations

    political figures and statistics

    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
    688
    +0.10
    0.5%
    314
    +0.10
    0.5%
    365
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.10
    0.02
    727
    +0.10
    0.02
    130
    +0.10
    0.02
    Negative Logits
     externalToEVAOnly
    -0.76
     Agric
    -0.75
    utical
    -0.71
    PsyNetMessage
    -0.70
    conservancy
    -0.69
    DonaldTrump
    -0.63
    æĺ
    -0.63
     Coul
    -0.61
    åĤ
    -0.58
     Tanz
    -0.58
    POSITIVE LOGITS
    er
    1.99
    est
    1.79
    ly
    1.50
    nesses
    1.31
    erness
    1.30
    itudinal
    1.24
    ened
    1.17
    erd
    1.13
    erton
    1.12
    ness
    1.09
    Activations Density 0.066%

    No Known Activations