© 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. 10559
    Prev
    Next
    INDEX
    Explanations

    terms related to microwaves and microwave technology

    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
    288
    +0.13
    0.6%
    187
    +0.12
    0.6%
    271
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    589
    +0.13
    0.02
    271
    +0.12
    0.02
    187
    +0.12
    0.02
    Negative Logits
    ACTED
    -0.69
     Dull
    -0.67
     Unified
    -0.66
    OUGH
    -0.62
    witz
    -0.60
    INGTON
    -0.60
    ENGTH
    -0.60
    tenance
    -0.59
    ignment
    -0.59
    ãĤĤ
    -0.57
    POSITIVE LOGITS
    helle
    1.19
    HAEL
    1.17
    ropolitan
    1.15
    roman
    1.10
    rones
    1.08
    ron
    1.01
    illin
    1.01
    rodu
    0.98
    rics
    0.98
    rom
    0.97
    Activations Density 0.027%

    No Known Activations