© 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. 2-MLP-SM
    11. 23772
    Prev
    Next
    INDEX
    Explanations

    mentions of specific street names and addresses

    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
    1.7%
    498
    +0.11
    0.6%
    297
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.30
    0.02
    125
    +0.11
    0.03
    46
    +0.10
    0.02
    Negative Logits
    ista
    -1.87
    batim
    -1.76
     Awards
    -1.75
    endas
    -1.75
    ably
    -1.64
    quez
    -1.63
    ogue
    -1.63
    chle
    -1.63
     Bros
    -1.58
     Stadium
    -1.56
    POSITIVE LOGITS
    ³
    1.68
    unnumbered
    1.63
     assumption
    1.53
    amyl
    1.49
     finger
    1.47
     droplet
    1.47
     uncertainty
    1.45
     drift
    1.44
     heartbeat
    1.44
     uptake
    1.42
    Activations Density 0.323%

    No Known Activations