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 49152
    5. 8-RES_FS49152-JB
    6. 26451
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and statistics related to events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.18
    0.8%
    378
    +0.13
    0.6%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.18
    0.03
    469
    +0.13
    0.02
    546
    +0.11
    0.02
    Negative Logits
     ast
    -0.68
     Harriet
    -0.68
     spans
    -0.65
    eph
    -0.60
     ASP
    -0.60
     Samar
    -0.59
     Imper
    -0.59
     undert
    -0.58
     Sapp
    -0.58
    sth
    -0.58
    POSITIVE LOGITS
    ĪĴ
    1.00
    Third
    0.88
    thirds
    0.83
    ĺħ
    0.81
    dyl
    0.81
    itone
    0.79
    third
    0.76
    VPN
    0.74
    iii
    0.73
    iliated
    0.72
    Activations Density 0.122%

    No Known Activations