© 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. 30793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high numerical values or significant amounts

    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
    432
    +0.14
    0.8%
    53
    +0.11
    0.6%
    382
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.18
    486
    +0.11
    0.12
    154
    +0.11
    0.11
    Negative Logits
    clin
    -1.52
    =/
    -1.47
     ballistic
    -1.35
     drinks
    -1.33
    enne
    -1.31
     jest
    -1.31
     meu
    -1.30
    ż
    -1.30
    ="
    -1.30
     nada
    -1.30
    POSITIVE LOGITS
    £
    3.74
    ĨĴ
    3.39
    Ħ
    3.30
    ĻĤ
    3.27
    ¬
    3.21
    ↵↵
    3.19
         ↵
    3.19
    ↵
    3.19
    ↵
    3.19
    <|outofrange|>
    3.19
    Activations Density 0.361%

    No Known Activations