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. 2571
    Prev
    Next
    INDEX
    Explanations

    phone numbers and technical information such as schema and server commands

    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
    373
    +0.14
    0.7%
    411
    +0.13
    0.6%
    295
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.02
    247
    +0.13
    0.04
    284
    +0.11
    0.05
    Negative Logits
     stacking
    -0.61
    ndra
    -0.59
     fray
    -0.57
    orically
    -0.56
    ynchronous
    -0.56
     chunk
    -0.55
     spirited
    -0.54
     curs
    -0.54
     prey
    -0.54
     round
    -0.53
    POSITIVE LOGITS
    Fax
    0.85
    INFO
    0.83
    éĹĺ
    0.78
    abc
    0.75
    228
    0.75
    499
    0.72
    877
    0.72
    -+-+
    0.72
    989
    0.71
    2020
    0.70
    Activations Density 0.482%

    No Known Activations