© 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. 24032
    Prev
    Next
    INDEX
    Explanations

    various forms of parentheses

    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
    156
    +0.23
    1.3%
    400
    +0.11
    0.6%
    16
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.23
    0.04
    112
    +0.11
    0.04
    489
    +0.10
    0.02
    Negative Logits
    ī
    -1.80
    Į
    -1.80
    Ī
    -1.59
    ·
    -1.53
    ·¸
    -1.45
    dern
    -1.41
    INGTON
    -1.38
    ¶
    -1.36
    geons
    -1.32
    ¼
    -1.32
    POSITIVE LOGITS
    """
    1.57
    mers
    1.50
    rape
    1.46
    seed
    1.44
     roles
    1.44
    ubert
    1.43
    github
    1.40
     role
    1.40
    otrop
    1.39
     mimics
    1.39
    Activations Density 0.096%

    No Known Activations