© 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 EvalsExportsAPI 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. 28469
    Prev
    Next
    INDEX
    Explanations

    terms related to database schema definitions and data types

    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
    466
    +0.12
    0.7%
    66
    +0.12
    0.7%
    327
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.12
    0.01
    66
    +0.12
    0.01
    482
    +0.11
    0.01
    Negative Logits
     desired
    -1.64
    ever
    -1.58
     chance
    -1.47
    rely
    -1.47
    č↵č↵
    -1.43
     appropriate
    -1.42
     slightest
    -1.42
    InstanceState
    -1.39
    yo
    -1.35
    icia
    -1.33
    POSITIVE LOGITS
    nell
    2.03
    piper
    1.74
    fish
    1.73
    ¼
    1.70
    leys
    1.69
    «
    1.66
    ĻĤ
    1.63
    ¦
    1.60
    ruptcy
    1.58
    uscript
    1.55
    Activations Density 0.024%

    No Known Activations