© 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. 2-MLP-SM
    11. 23633
    Prev
    Next
    INDEX
    Explanations

    references to companies and corporate entities

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    82
    +0.13
    0.7%
    411
    +0.12
    0.7%
    430
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.13
    0.03
    411
    +0.12
    0.06
    461
    +0.12
    0.08
    Negative Logits
     attention
    -1.81
    girl
    -1.63
     terrorism
    -1.57
    acts
    -1.55
    ?_
    -1.50
     violence
    -1.49
    strength
    -1.47
     terrible
    -1.46
    fires
    -1.43
     aggression
    -1.42
    POSITIVE LOGITS
     manually
    1.77
    ibernate
    1.63
     separately
    1.50
    ackage
    1.50
     individually
    1.48
    antry
    1.48
    irect
    1.47
     privately
    1.47
    AP
    1.45
    apter
    1.43
    Activations Density 2.284%

    No Known Activations