© 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. 269
    Prev
    Next
    INDEX
    Explanations

    names containing the elements "ior" and "gio"

    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
    728
    +0.12
    0.5%
    699
    +0.11
    0.5%
    499
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.12
    0.01
    284
    +0.11
    0.01
    499
    +0.11
    0.01
    Negative Logits
    erness
    -0.76
    sheet
    -0.75
    ivity
    -0.68
    alter
    -0.66
    lished
    -0.66
    shell
    -0.64
    sheets
    -0.63
    INESS
    -0.63
    puter
    -0.63
    yssey
    -0.62
    POSITIVE LOGITS
    gio
    1.47
    ior
    1.03
    ama
    0.96
    iculture
    0.85
    amas
    0.84
    iasis
    0.83
    IOR
    0.81
    andom
    0.79
    amic
    0.78
    ity
    0.78
    Activations Density 0.023%

    No Known Activations