© 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. 2-MLP-SM
    11. 24932
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting indicators

    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
    47
    +0.11
    0.6%
    247
    +0.10
    0.6%
    239
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.11
    0.09
    240
    +0.10
    0.04
    217
    +0.09
    0.08
    Negative Logits
     notice
    -1.77
     careful
    -1.57
    ))$.
    -1.56
    ximately
    -1.51
     heart
    -1.50
    )}$.
    -1.47
     feeling
    -1.45
    \)
    -1.43
     KNOW
    -1.43
     sincere
    -1.41
    POSITIVE LOGITS
    lei
    1.71
     era
    1.68
     employs
    1.68
    ÃŃf
    1.67
    ovsk
    1.61
     encodes
    1.53
    iewicz
    1.52
    ène
    1.52
     depends
    1.51
    fors
    1.51
    Activations Density 0.905%

    No Known Activations