© 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. 29015
    Prev
    Next
    INDEX
    Explanations

    mentions of the year 1980

    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
    +0.12
    0.7%
    250
    +0.11
    0.6%
    436
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.12
    0.02
    490
    +0.11
    0.02
    145
    +0.11
    0.02
    Negative Logits
    hab
    -1.76
     doubt
    -1.63
     whole
    -1.60
     power
    -1.58
     sympath
    -1.54
     connection
    -1.52
     pity
    -1.51
     suspicion
    -1.50
     kind
    -1.48
     remotely
    -1.47
    POSITIVE LOGITS
    itudinal
    1.84
    icolor
    1.77
    s
    1.73
    ¿½
    1.73
    ental
    1.71
    enthal
    1.64
    ģ
    1.64
    ienn
    1.62
    stone
    1.61
    Ń
    1.58
    Activations Density 0.020%

    No Known Activations