© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 25640
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic fields and their properties

    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
    23
    +0.20
    1.1%
    301
    +0.11
    0.6%
    289
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.20
    0.06
    410
    +0.11
    0.04
    208
    +0.11
    0.04
    Negative Logits
    =”
    -1.76
    etc
    -1.64
    ukin
    -1.53
     ng
    -1.52
    ~=
    -1.50
    pieces
    -1.50
    ivos
    -1.48
    izon
    -1.48
     atmosphere
    -1.46
    %=
    -1.46
    POSITIVE LOGITS
    ↵↵
    1.76
    1.76
    <|outofrange|>
    1.76
    ↵
    1.76
    1.76
    1.76
    ↵
    1.76
    ↵  ³³³
    1.76
    č↵
    1.76
    1.76
    Activations Density 1.013%

    No Known Activations