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 3072
    5. 8-RES_FS3072-JB
    6. 2949
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    106
    +0.14
    0.7%
    276
    +0.13
    0.6%
    549
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.08
    232
    +0.13
    0.08
    106
    +0.12
    0.07
    Negative Logits
    ãĥ¤
    -0.80
    ãĥ¡
    -0.73
    ãĥ¼ãĥ³
    -0.71
    ãĥ¯ãĥ³
    -0.68
    ãĥ
    -0.66
    Ö¼
    -0.66
    ×Ļ
    -0.66
    phia
    -0.65
    idad
    -0.64
     Pwr
    -0.63
    POSITIVE LOGITS
    lasses
    1.29
    regate
    1.22
    aroo
    1.09
    oing
    1.09
    ratulations
    1.07
    lass
    1.06
    lia
    1.00
    regor
    0.97
    roup
    0.95
    nam
    0.93
    Activations Density 0.878%

    No Known Activations