© 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. 30561
    Prev
    Next
    INDEX
    Explanations

    keywords related to asynchronous processes or tasks

    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
    292
    +0.16
    0.9%
    410
    +0.12
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    292
    +0.12
    0.01
    71
    +0.11
    0.01
    Negative Logits
    other
    -1.69
     absence
    -1.67
     presence
    -1.65
     Where
    -1.62
     midst
    -1.55
     Briefly
    -1.55
     Then
    -1.46
     whom
    -1.44
     largest
    -1.42
    athered
    -1.41
    POSITIVE LOGITS
    "}](#
    2.06
    aña
    2.01
    IFIC
    1.81
    -âĤ¬
    1.77
    enstein
    1.74
    ción
    1.57
    emos
    1.57
    ordo
    1.54
    ulation
    1.51
    cad
    1.50
    Activations Density 0.014%

    No Known Activations