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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27211
    Prev
    Next
    INDEX
    Explanations

    mentions of distances in miles or kilometers

    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
    457
    +0.13
    0.7%
    325
    +0.12
    0.7%
    499
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.13
    0.03
    499
    +0.12
    0.03
    37
    +0.12
    0.02
    Negative Logits
    yers
    -1.80
    athing
    -1.66
    ches
    -1.59
     researchers
    -1.58
     lesbian
    -1.52
    ishers
    -1.50
     Students
    -1.48
     Teachers
    -1.47
     authors
    -1.47
    lying
    -1.46
    POSITIVE LOGITS
    ®
    2.52
    ĩ
    2.39
    µ
    2.38
    ¸
    2.37
    ¹
    2.34
    ¶
    2.28
    į
    2.10
    Į
    2.01
    ÃŃvel
    1.99
    ģ
    1.93
    Activations Density 0.019%

    No Known Activations