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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 4531
    Prev
    Next
    INDEX
    Explanations

    mentions of product collaborations and business agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    480
    +0.42
    2.3%
    447
    +0.27
    1.5%
    87
    +0.26
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.42
    0.14
    480
    +0.27
    0.05
    464
    +0.26
    0.11
    Negative Logits
     destro
    -0.75
     agre
    -0.69
     arrang
    -0.69
     prest
    -0.68
     disg
    -0.66
     withd
    -0.66
     explan
    -0.66
    nesday
    -0.65
    uggest
    -0.64
    omever
    -0.64
    POSITIVE LOGITS
     Profile
    0.89
     âĵĺ
    0.81
     Facts
    0.77
     Forums
    0.74
     Overview
    0.70
     Background
    0.70
     Released
    0.69
     Releases
    0.69
     Release
    0.69
     Transcript
    0.69
    Activations Density 1.985%

    No Known Activations