© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 26819
    Prev
    Next
    INDEX
    Explanations

    articles related to patents or inventions

    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
    32
    +0.15
    0.8%
    411
    +0.13
    0.7%
    443
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.15
    0.01
    32
    +0.13
    0.01
    480
    +0.13
    0.01
    Negative Logits
    charge
    -1.59
     discrimination
    -1.39
     advance
    -1.33
    Cs
    -1.32
    tight
    -1.31
     avoidance
    -1.29
     harassment
    -1.27
     diversity
    -1.25
    ype
    -1.25
    %\
    -1.23
    POSITIVE LOGITS
    umbent
    1.67
    lei
    1.47
     unpublished
    1.46
    angel
    1.43
    launchpad
    1.42
    asket
    1.42
    ivir
    1.42
    nen
    1.42
    nier
    1.41
     astr
    1.41
    Activations Density 0.028%

    No Known Activations