© 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. 24061
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and governance structures

    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
    486
    +0.15
    0.8%
    156
    +0.13
    0.7%
    479
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.15
    0.09
    81
    +0.13
    0.06
    486
    +0.11
    -0.02
    Negative Logits
    ¬
    -2.82
    »
    -2.55
    Ļ
    -2.53
    IJ
    -2.45
    ¤
    -2.44
    ·
    -2.41
    ī
    -2.41
    ij
    -2.34
    ¿
    -2.34
    Ģ
    -2.27
    POSITIVE LOGITS
    efs
    1.77
    _"
    1.71
    arding
    1.69
    >",
    1.60
    _."
    1.60
    .")
    1.59
    ect
    1.56
    (_
    1.52
    abilities
    1.51
    .",
    1.49
    Activations Density 3.812%

    No Known Activations