© 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. 25257
    Prev
    Next
    INDEX
    Explanations

    references to specific weeks in a time period

    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
    252
    +0.16
    0.9%
    116
    +0.10
    0.6%
    310
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.16
    0.04
    281
    +0.10
    0.02
    223
    +0.10
    0.02
    Negative Logits
    Ļª
    -1.61
    ĻĤ
    -1.57
    ±
    -1.55
     favor
    -1.51
    ĩ
    -1.48
     accompany
    -1.45
     delegates
    -1.44
     hundred
    -1.41
    apters
    -1.34
     refugees
    -1.33
    POSITIVE LOGITS
    addam
    1.67
    iph
    1.52
    edic
    1.51
    oding
    1.51
    ing
    1.51
     manufacture
    1.50
    ed
    1.50
    ovirus
    1.46
    forge
    1.45
    abi
    1.44
    Activations Density 0.264%

    No Known Activations