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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 46120
    Prev
    Next
    INDEX
    Explanations

    the presence of a particular character or symbol representing a brand

    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
    314
    +0.11
    0.5%
    373
    +0.11
    0.5%
    480
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.11
    0.10
    352
    +0.11
    0.10
    426
    +0.10
    0.08
    Negative Logits
     scattering
    -0.81
     DPR
    -0.73
     lodging
    -0.64
     scatter
    -0.63
     purse
    -0.62
     guiActiveUnfocused
    -0.61
     Ukrain
    -0.61
     blender
    -0.61
     muse
    -0.61
     Counsel
    -0.60
    POSITIVE LOGITS
    º
    1.15
    ¹
    1.14
    £
    1.03
    Į
    0.99
    ı
    0.96
    į
    0.94
    Ĵ
    0.93
    ¿
    0.92
    §
    0.90
    agree
    0.89
    Activations Density 0.195%

    No Known Activations