© 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. 2-MLP-SM
    11. 24914
    Prev
    Next
    INDEX
    Explanations

    keywords related to cloud computing and data flow in programming contexts

    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
    +0.30
    1.8%
    400
    +0.13
    0.7%
    216
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.30
    0.09
    56
    +0.13
    0.11
    343
    +0.12
    0.09
    Negative Logits
     Wikipedia
    -1.98
    inux
    -1.95
    wiki
    -1.95
     wiki
    -1.91
    jsfiddle
    -1.80
     Twitter
    -1.75
     blockchain
    -1.75
    aires
    -1.74
    blogs
    -1.74
    forge
    -1.74
    POSITIVE LOGITS
    geant
    1.63
    uther
    1.60
    ÃĤ
    1.49
    Appro
    1.49
    DECL
    1.45
    ALK
    1.43
    ***
    1.42
    LLOW
    1.41
    LEV
    1.41
     Aim
    1.38
    Activations Density 1.260%

    No Known Activations