© 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. 23913
    Prev
    Next
    INDEX
    Explanations

    the phrase "By" indicating authorship or source attribution in various contexts

    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
    455
    +0.13
    0.7%
    237
    +0.13
    0.7%
    16
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.13
    0.03
    135
    +0.13
    0.03
    16
    +0.12
    0.03
    Negative Logits
    ī
    -3.42
    «
    -3.31
    ³
    -3.17
    ¨
    -3.16
    ²
    -3.16
    ©
    -3.13
    ª
    -3.09
    ¦
    -3.09
    ±
    -3.06
    ½
    -3.01
    POSITIVE LOGITS
    aries
    1.89
    eral
    1.64
    ück
    1.62
    rael
    1.59
    erals
    1.55
    als
    1.55
    issions
    1.54
    zar
    1.50
    arias
    1.48
    raph
    1.48
    Activations Density 0.242%

    No Known Activations