© 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. 25091
    Prev
    Next
    INDEX
    Explanations

    empty spaces or gaps in the text

    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
    220
    +0.12
    0.7%
    77
    +0.11
    0.6%
    352
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.12
    0.04
    220
    +0.11
    0.04
    352
    +0.10
    0.02
    Negative Logits
    #{$
    -1.99
     Democr
    -1.58
    @
    -1.54
    ãģ¾ãģĽ
    -1.52
    ires
    -1.52
     @
    -1.50
     (“
    -1.49
    ---|---
    -1.46
    ↵³³
    -1.45
    Simplify
    -1.43
    POSITIVE LOGITS
     injured
    1.60
    ilst
    1.50
    ļ
    1.50
    ĸ´
    1.48
    ¸
    1.47
    FFIRMED
    1.43
    Īĺ
    1.36
    1.36
      ↵
    1.36
    1.36
    Activations Density 0.197%

    No Known Activations