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 6144
    5. 8-RES_FS6144-JB
    6. 5451
    Prev
    Next
    INDEX
    Explanations

    contrasting pairs or opposing entities within a larger context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    459
    +0.16
    0.7%
    300
    +0.11
    0.5%
    756
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.16
    0.06
    300
    +0.11
    0.07
    384
    +0.10
    0.05
    Negative Logits
     ILCS
    -0.62
    Join
    -0.60
     Donation
    -0.59
    meet
    -0.58
     Authorization
    -0.56
    Avg
    -0.56
    Previous
    -0.55
    "},"
    -0.55
     Blessing
    -0.54
     Annotations
    -0.53
    POSITIVE LOGITS
     merely
    0.74
    aurus
    0.72
     opted
    0.70
    ãĥł
    0.70
    anges
    0.68
     went
    0.67
    retty
    0.66
    ãģ®éŃĶ
    0.66
    ombie
    0.65
     stayed
    0.65
    Activations Density 0.657%

    No Known Activations