© 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 EvalsExportsinterp-engineNEWAPI 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. 30291
    Prev
    Next
    INDEX
    Explanations

    terms related to deprivation or loss

    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
    224
    +0.14
    0.8%
    365
    +0.13
    0.8%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.14
    0.01
    251
    +0.13
    0.01
    182
    +0.12
    0.01
    Negative Logits
    Ĥ¬
    -1.81
    illance
    -1.63
    ¬
    -1.63
    ĨĴ
    -1.61
    ¯
    -1.51
    Ķ
    -1.50
     full
    -1.47
    §
    -1.46
    woke
    -1.39
    ¸
    -1.39
    POSITIVE LOGITS
     era
    1.87
     settings
    1.83
     occasions
    1.77
     regime
    1.64
     menus
    1.61
     regimes
    1.61
     contexts
    1.55
    nament
    1.54
    erior
    1.53
    imento
    1.50
    Activations Density 0.021%

    No Known Activations