© 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. 24306
    Prev
    Next
    INDEX
    Explanations

    comparisons or relationships involving symbols and operators

    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
    +0.40
    2.4%
    25
    +0.16
    1.0%
    88
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.40
    0.11
    25
    +0.16
    0.06
    368
    +0.14
    0.01
    Negative Logits
    º
    -2.59
    -2.48
    ↵
    -2.48
    <|outofrange|>
    -2.48
                ↵
    -2.48
    ↵  ↵
    -2.48
    ↵
    -2.48
    <|outofrange|>
    -2.48
    -2.48
    ↵
    -2.48
    POSITIVE LOGITS
    PRESS
    1.40
    \%
    1.37
    TRA
    1.36
    AML
    1.33
    ("<
    1.32
    \%$
    1.31
    IFN
    1.30
    ^**
    1.28
    arrest
    1.28
    PG
    1.25
    Activations Density 3.234%

    No Known Activations