© 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 EvalsExportsAPI 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. 5684
    Prev
    Next
    INDEX
    Explanations

    names of breweries and specific types of beer

    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
    87
    +0.32
    1.7%
    447
    +0.18
    1.0%
    481
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.32
    0.09
    659
    +0.18
    0.08
    145
    +0.12
    0.07
    Negative Logits
    etheless
    -0.58
     amplified
    -0.57
     inherit
    -0.57
     charge
    -0.57
     replace
    -0.56
     disabled
    -0.55
     guid
    -0.55
     separatist
    -0.55
     depreciation
    -0.55
     separation
    -0.55
    POSITIVE LOGITS
    ona
    0.87
    inda
    0.86
    onia
    0.85
    avia
    0.82
    isha
    0.81
    oya
    0.81
    ava
    0.80
    leys
    0.78
    Fest
    0.76
    ora
    0.76
    Activations Density 0.426%

    No Known Activations