Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23587
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sing" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    167
    +0.13
    0.6%
    439
    +0.12
    0.6%
    406
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.13
    0.01
    154
    +0.12
    0.01
    423
    +0.10
    0.01
    Negative Logits
     VICE
    -0.82
     SOFTWARE
    -0.64
     Ples
    -0.63
     bis
    -0.60
    etheless
    -0.60
    izons
    -0.60
     Stur
    -0.60
    adeon
    -0.59
    ````
    -0.59
    utterstock
    -0.59
    POSITIVE LOGITS
    ularity
    1.48
    apore
    1.47
    leton
    1.29
    lest
    1.24
    leness
    1.17
    les
    1.17
    lers
    1.15
    ular
    1.11
    ling
    1.11
    rab
    1.04
    Activations Density 0.021%

    No Known Activations