© 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. 23292
    Prev
    Next
    INDEX
    Explanations

    HTML tags with specific attributes

    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
    49
    +0.12
    0.7%
    422
    +0.12
    0.7%
    284
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.12
    0.01
    318
    +0.12
    0.00
    378
    +0.11
    0.00
    Negative Logits
    ļ
    -3.05
    ¾
    -2.86
    ²
    -2.85
    ¿½
    -2.82
    µ
    -2.80
    ĻĤ
    -2.78
    ®
    -2.78
    ½
    -2.73
    Į
    -2.69
    Ń
    -2.68
    POSITIVE LOGITS
     because
    1.58
    etin
    1.56
    because
    1.43
    iii
    1.43
    imer
    1.42
    ough
    1.42
    jest
    1.40
     sometime
    1.36
    AFFIRMED
    1.35
    ocarcin
    1.32
    Activations Density 0.134%

    No Known Activations