© 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. 25766
    Prev
    Next
    INDEX
    Explanations

    references to physical movement

    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
    208
    +0.14
    0.8%
    179
    +0.13
    0.7%
    202
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.14
    0.03
    212
    +0.13
    0.02
    107
    +0.12
    0.02
    Negative Logits
     constraints
    -1.69
     checkpoint
    -1.66
     neighborhood
    -1.51
     corners
    -1.46
     neighbors
    -1.45
     directly
    -1.42
    ://
    -1.38
     decomposition
    -1.37
     neighborhoods
    -1.37
     own
    -1.36
    POSITIVE LOGITS
    bred
    1.70
    wise
    1.64
    ancers
    1.63
    ynom
    1.46
    ly
    1.44
    menopausal
    1.41
    wer
    1.34
    \]](
    1.33
    chle
    1.32
     Yorker
    1.32
    Activations Density 0.005%

    No Known Activations