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. 21657
    Prev
    Next
    INDEX
    Explanations

    terms related to legal investigations and criminal charges

    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
    373
    +0.22
    1.2%
    480
    +0.20
    1.0%
    393
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.22
    0.01
    288
    +0.20
    0.12
    564
    +0.20
    0.06
    Negative Logits
    ãĥ£
    -0.60
    Flickr
    -0.60
    20439
    -0.57
    Merit
    -0.57
    GAN
    -0.56
    ãģ¾
    -0.56
    éĸ
    -0.56
    osaurs
    -0.54
    Pg
    -0.51
    ãĤ£
    -0.50
    POSITIVE LOGITS
     withd
    0.62
     rul
    0.62
    anwhile
    0.59
    theless
    0.56
     LM
    0.53
    ificate
    0.53
    etheless
    0.53
     tyr
    0.52
     secondly
    0.52
     skelet
    0.51
    Activations Density 2.233%

    No Known Activations