© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23958
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.18
    1.0%
    271
    +0.17
    1.0%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.06
    271
    +0.17
    0.08
    56
    +0.14
    0.13
    Negative Logits
    ĭ
    -2.14
    ī
    -2.13
    IJ
    -2.00
    İ
    -1.91
    į
    -1.91
    §
    -1.88
    ¹
    -1.84
    ¤
    -1.84
    Ĭ
    -1.81
    ·
    -1.77
    POSITIVE LOGITS
     feeling
    1.63
    áĢ¯
    1.61
    hab
    1.47
     reputation
    1.46
    å¿ĥ
    1.43
     Hipp
    1.39
    had
    1.39
     friendly
    1.37
    gest
    1.36
    oscopic
    1.34
    Activations Density 2.933%

    No Known Activations