© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4559
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and details

    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
    447
    +0.17
    0.8%
    149
    +0.10
    0.4%
    634
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.17
    0.05
    570
    +0.10
    0.02
    566
    +0.08
    0.04
    Negative Logits
    kat
    -0.68
    itus
    -0.64
    tone
    -0.64
    Appearance
    -0.60
     ILCS
    -0.60
    authent
    -0.59
    hid
    -0.58
    idia
    -0.56
    Chel
    -0.55
     offic
    -0.55
    POSITIVE LOGITS
     fewer
    1.08
     billions
    1.03
     roughly
    1.03
     nearly
    1.03
     $
    1.03
     substantially
    0.99
     considerably
    0.98
     significantly
    0.98
     approximately
    0.97
     plenty
    0.97
    Activations Density 0.258%

    No Known Activations