© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41748
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and taxation

    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
    481
    +0.12
    0.5%
    407
    +0.11
    0.5%
    418
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.03
    362
    +0.11
    0.03
    418
    +0.11
    0.02
    Negative Logits
    DragonMagazine
    -0.78
    hent
    -0.75
    artifacts
    -0.74
    pecially
    -0.72
    Streamer
    -0.68
    asy
    -0.67
    âĸĪâĸĪâĸĪâĸĪ
    -0.67
    VPN
    -0.66
    aqu
    -0.66
    cest
    -0.66
    POSITIVE LOGITS
     GDP
    1.68
     income
    1.28
     incomes
    1.25
     revenues
    1.25
     earnings
    1.16
     taxable
    1.13
     revenue
    1.13
     wages
    1.10
     budgets
    1.10
     coffers
    1.10
    Activations Density 0.088%

    No Known Activations