© 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. 24148
    Prev
    Next
    INDEX
    Explanations

    elements of structured data or key-value pairs

    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
    23
    +0.22
    1.3%
    156
    +0.19
    1.1%
    443
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.22
    0.14
    492
    +0.19
    0.07
    146
    +0.11
    0.06
    Negative Logits
    ¿½
    -3.63
    Ĭ
    -3.05
    Ĥ¬
    -2.88
    ij
    -2.88
    ŀ
    -2.86
    Ļª
    -2.80
    ĥ½
    -2.80
    ²
    -2.74
    ķ
    -2.73
    °
    -2.71
    POSITIVE LOGITS
     apologize
    1.56
     recovery
    1.51
    ne
    1.50
    rely
    1.50
     confidentiality
    1.49
     congressional
    1.47
     researchers
    1.43
     contrary
    1.42
     decline
    1.41
     _
    1.41
    Activations Density 3.184%

    No Known Activations