© 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. 2-MLP-SM
    11. 23147
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to errors and rights in commercial contexts

    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
    469
    +0.13
    0.7%
    107
    +0.11
    0.6%
    427
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.13
    -0.01
    424
    +0.11
    0.02
    110
    +0.11
    0.06
    Negative Logits
    Ļª
    -2.02
     sarc
    -1.52
    cribing
    -1.49
    être
    -1.48
    APTER
    -1.46
     attent
    -1.45
    raised
    -1.45
     chalk
    -1.43
    mounted
    -1.41
    urred
    -1.40
    POSITIVE LOGITS
    /-/
    1.77
    ?”
    1.68
    nai
    1.66
     alone
    1.65
    onia
    1.65
    /](
    1.63
    amycin
    1.60
    ów
    1.59
    igion
    1.55
    oku
    1.53
    Activations Density 3.047%

    No Known Activations