© 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. 25186
    Prev
    Next
    INDEX
    Explanations

    articles and determiners used in descriptions

    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
    347
    +0.16
    0.9%
    452
    +0.11
    0.6%
    330
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.16
    0.02
    291
    +0.11
    0.02
    168
    +0.11
    0.02
    Negative Logits
    ninger
    -1.63
    terest
    -1.63
     large
    -1.61
    ning
    -1.58
    cept
    -1.54
     sandwich
    -1.52
     office
    -1.51
     publication
    -1.46
    boro
    -1.42
     bars
    -1.41
    POSITIVE LOGITS
    ł
    2.22
    ļ
    2.17
    Ĥ¬
    2.12
    Ļ
    2.11
    ¯
    2.08
    IJ
    2.08
    ĺ
    2.05
    Ĺ
    2.02
    ¿½
    1.93
    Ļª
    1.88
    Activations Density 0.059%

    No Known Activations