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 1536
    5. 8-RES_FS1536-JB
    6. 303
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases beginning with "at the other end of"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    589
    +0.11
    0.5%
    16
    +0.10
    0.5%
    296
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.11
    16
    +0.10
    0.09
    476
    +0.09
    0.07
    Negative Logits
     Cosponsors
    -0.67
     nonetheless
    -0.64
     pets
    -0.63
     nevertheless
    -0.63
    rw
    -0.61
    folk
    -0.60
    ologically
    -0.60
    ants
    -0.60
    usercontent
    -0.59
    cause
    -0.59
    POSITIVE LOGITS
     spectrum
    0.81
     hostilities
    0.77
     runway
    0.76
     rope
    0.73
    yssey
    0.69
     nowhere
    0.69
    enium
    0.67
     session
    0.67
    veyard
    0.66
     sentence
    0.66
    Activations Density 1.796%

    No Known Activations