© 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. 0-MLP-SM
    11. 29113
    Prev
    Next
    INDEX
    Explanations

    instances of bracketed or list-like structures in 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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    359
    +0.15
    0.8%
    464
    +0.12
    0.7%
    4
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.15
    0.06
    258
    +0.12
    0.06
    155
    +0.11
    0.05
    Negative Logits
    ħ
    -4.37
    ĻĤ
    -4.20
    -3.80
    ↵↵
    -3.80
    ↵            ↵
    -3.80
    <|outofrange|>
    -3.80
    ↵
    -3.80
    ↵Č
    -3.80
    ↵
    -3.80
    <|outofrange|>
    -3.80
    POSITIVE LOGITS
    ACH
    1.45
     consent
    1.43
     immun
    1.43
    Declaration
    1.40
    Click
    1.37
     Immun
    1.36
      ↵
    1.36
     Mathematics
    1.34
    atitis
    1.33
     supers
    1.30
    Activations Density 0.055%

    No Known Activations