© 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. 28601
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or context involving "Ottawa" and "Holocaust."

    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
    178
    +0.14
    0.8%
    502
    +0.13
    0.7%
    423
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.01
    190
    +0.13
    0.01
    1
    +0.11
    0.01
    Negative Logits
    ĥ½
    -1.60
     hardness
    -1.49
     imprint
    -1.44
     tens
    -1.43
     appearance
    -1.42
     blocker
    -1.35
     pitch
    -1.34
     antagonist
    -1.33
     beta
    -1.32
     emitter
    -1.32
    POSITIVE LOGITS
    to
    2.04
    tawa
    1.61
    aceae
    1.58
    TO
    1.55
    amed
    1.50
    by
    1.48
    pton
    1.48
    respectively
    1.47
    ospital
    1.43
    per
    1.42
    Activations Density 0.128%

    No Known Activations