© 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. 29074
    Prev
    Next
    INDEX
    Explanations

    specific years, particularly the year 1971

    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
    269
    +0.14
    0.8%
    58
    +0.12
    0.7%
    110
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.14
    0.02
    269
    +0.12
    0.02
    97
    +0.11
    0.02
    Negative Logits
    arts
    -1.77
    ights
    -1.72
     favor
    -1.61
     tears
    -1.55
     behold
    -1.54
    lder
    -1.53
    asts
    -1.52
    ls
    -1.50
    ast
    -1.45
     moderate
    -1.44
    POSITIVE LOGITS
    ENCE
    1.83
    ,#
    1.47
    unnumbered
    1.46
    ificial
    1.46
    uscript
    1.44
    ģ
    1.42
    erals
    1.39
    uary
    1.37
    ¿½
    1.36
    ZX
    1.36
    Activations Density 4.722%

    No Known Activations