© 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. 26703
    Prev
    Next
    INDEX
    Explanations

    consistent and repetitive patterns or structures in sentences

    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
    390
    +0.13
    0.7%
    296
    +0.12
    0.7%
    178
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.55
    56
    +0.12
    0.18
    203
    +0.11
    0.38
    Negative Logits
    į
    -3.65
    Į
    -3.32
    ħ
    -3.29
    Ń
    -3.13
    ¹
    -3.13
    ¯
    -3.08
    ij
    -3.01
    Ŀ
    -2.80
    ¦
    -2.75
    ĥ
    -2.73
    POSITIVE LOGITS
    quo
    1.82
    estones
    1.68
    uty
    1.65
    enta
    1.53
    lake
    1.47
     Redistributions
    1.40
    agent
    1.39
     trademark
    1.37
    ishes
    1.32
     Nash
    1.31
    Activations Density 3.578%

    No Known Activations