© 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. 12439
    Prev
    Next
    INDEX
    Explanations

    locations or names containing the word "Ell"

    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
    561
    +0.10
    0.4%
    582
    +0.09
    0.4%
    476
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.10
    0.01
    232
    +0.09
    0.01
    582
    +0.09
    0.01
    Negative Logits
     Anthem
    -0.67
     visually
    -0.65
    oglu
    -0.64
    ItemTracker
    -0.63
     parap
    -0.62
    ãĤ´ãĥ³
    -0.60
     Popular
    -0.60
     derog
    -0.60
    CHAR
    -0.60
    ãĥ£
    -0.59
    POSITIVE LOGITS
    ipt
    1.40
    izabeth
    1.20
    igible
    1.19
    sworth
    1.12
    enium
    1.07
    inia
    1.01
    iot
    1.00
    sburg
    1.00
    wright
    1.00
    issa
    0.99
    Activations Density 0.023%

    No Known Activations