© 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. 24067
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to medical studies

    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
    +0.17
    1.0%
    104
    +0.11
    0.6%
    367
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.17
    0.02
    159
    +0.11
    0.02
    402
    +0.11
    0.03
    Negative Logits
    «
    -2.13
    Ĥ
    -2.08
    -2.06
    ↵
    -2.06
    <|outofrange|>
    -2.06
    <|outofrange|>
    -2.06
    -2.06
    ↵
    -2.06
    ↵↵
    -2.06
    ↵
    -2.06
    POSITIVE LOGITS
    ils
    1.98
     powers
    1.56
     heck
    1.53
    keit
    1.48
     pans
    1.46
    nel
    1.45
    poons
    1.44
    imals
    1.42
    ets
    1.40
     visions
    1.39
    Activations Density 0.186%

    No Known Activations