© 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. 0-MLP-SM
    11. 30212
    Prev
    Next
    INDEX
    Explanations

    repeated phrases that emphasize the word "We."

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    356
    +0.13
    0.7%
    420
    +0.11
    0.6%
    42
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.13
    0.07
    348
    +0.11
    0.06
    39
    +0.11
    0.06
    Negative Logits
    erty
    -1.92
    ){#
    -1.68
    pone
    -1.64
    releases
    -1.49
    ondon
    -1.47
    oint
    -1.43
    tm
    -1.41
     themselves
    -1.39
    rates
    -1.38
    blogspot
    -1.38
    POSITIVE LOGITS
     accomplished
    1.53
     sheaf
    1.47
     smug
    1.41
    ·¸
    1.38
    ,--
    1.36
    ĻĤ
    1.35
    iles
    1.30
     bedside
    1.29
     indispensable
    1.28
    ALLY
    1.28
    Activations Density 0.086%

    No Known Activations