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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11730
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal beliefs and life decisions

    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
    418
    +0.11
    0.5%
    202
    +0.11
    0.5%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.11
    0.08
    43
    +0.11
    0.06
    546
    +0.09
    0.07
    Negative Logits
    chin
    -0.74
    iple
    -0.68
    ania
    -0.67
    coni
    -0.67
    utive
    -0.65
    lier
    -0.64
    chell
    -0.62
    quartered
    -0.62
    iny
    -0.61
    ighed
    -0.60
    POSITIVE LOGITS
     albeit
    1.37
     regardless
    1.18
     irrespective
    1.11
     yeah
    1.02
     insofar
    1.00
     anyway
    0.98
     though
    0.97
     although
    0.97
     lest
    0.93
     preferably
    0.93
    Activations Density 0.313%

    No Known Activations