© 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. 28507
    Prev
    Next
    INDEX
    Explanations

    mentions of the city Indianapolis

    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
    182
    +0.14
    0.9%
    100
    +0.11
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.14
    0.02
    370
    +0.11
    0.01
    449
    +0.11
    0.01
    Negative Logits
    usterity
    -2.07
    ĥ½
    -1.89
    inned
    -1.80
     your
    -1.74
    ı
    -1.62
    ributes
    -1.57
     certain
    -1.57
    ancies
    -1.56
    aster
    -1.53
    edes
    -1.51
    POSITIVE LOGITS
    genstein
    1.84
    igent
    1.82
    ville
    1.77
    leen
    1.72
    illac
    1.70
    inson
    1.69
    vier
    1.62
    yard
    1.60
     Rapids
    1.58
    pere
    1.55
    Activations Density 0.015%

    No Known Activations