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. 8317
    Prev
    Next
    INDEX
    Explanations

    words related to financial matters or economic concepts

    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
    269
    +0.12
    0.6%
    526
    +0.10
    0.5%
    654
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.12
    0.04
    568
    +0.10
    0.04
    684
    +0.10
    0.03
    Negative Logits
    YA
    -0.71
    UE
    -0.70
    oke
    -0.69
    女
    -0.63
    ooo
    -0.62
    iva
    -0.62
    MSN
    -0.61
    STAR
    -0.60
    oker
    -0.60
    UES
    -0.59
    POSITIVE LOGITS
    hang
    1.06
    whelming
    1.00
    tones
    0.99
    comes
    0.98
    capacity
    0.96
    haul
    0.93
    priced
    0.93
    drive
    0.92
    clock
    0.91
    sites
    0.89
    Activations Density 0.072%

    No Known Activations