© 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. 0-MLP-SM
    11. 26740
    Prev
    Next
    INDEX
    Explanations

    terms related to properties of materials in physics

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    111
    +0.12
    0.7%
    291
    +0.12
    0.7%
    189
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.12
    0.01
    359
    +0.12
    0.01
    83
    +0.12
    0.01
    Negative Logits
     Eve
    -1.63
     Snow
    -1.50
    mo
    -1.47
    akin
    -1.45
    tox
    -1.44
    hin
    -1.40
    ene
    -1.39
     Den
    -1.37
     Mil
    -1.34
    hores
    -1.34
    POSITIVE LOGITS
    "}](#
    1.81
     situation
    1.72
     regime
    1.65
     exception
    1.60
    thirds
    1.55
     regimes
    1.55
    FLD
    1.54
    atted
    1.51
    @
    1.50
     status
    1.50
    Activations Density 0.011%

    No Known Activations