© 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. 26533
    Prev
    Next
    INDEX
    Explanations

    terms related to gravitational forces and concepts 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
    +0.16
    1.0%
    156
    +0.13
    0.8%
    22
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.16
    0.04
    228
    +0.13
    0.03
    164
    +0.13
    0.03
    Negative Logits
     planned
    -1.67
    eks
    -1.61
     plotted
    -1.57
    aring
    -1.50
    iling
    -1.50
     choose
    -1.49
    ÑĤÑĮ
    -1.45
     reasoned
    -1.45
     raped
    -1.44
     confess
    -1.43
    POSITIVE LOGITS
    ¡
    2.48
    ģ
    2.27
    Ł
    2.06
    £
    1.99
    ĺ
    1.86
    Ħ
    1.83
    µ
    1.75
    ĻĤ
    1.75
    opa
    1.73
    ŀ
    1.71
    Activations Density 2.895%

    No Known Activations