© 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. 29861
    Prev
    Next
    INDEX
    Explanations

    references to ecological concepts and issues

    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
    156
    +0.33
    2.0%
    360
    +0.11
    0.7%
    103
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.33
    0.01
    103
    +0.11
    0.01
    266
    +0.11
    0.01
    Negative Logits
    ureus
    -1.58
    urop
    -1.58
    aliana
    -1.50
    éri
    -1.42
     Arab
    -1.39
     '</
    -1.34
    rocy
    -1.34
     Arabian
    -1.32
    *).
    -1.30
     continuous
    -1.26
    POSITIVE LOGITS
    ĻĤ
    1.96
    erals
    1.64
    ISPR
    1.59
    "}](#
    1.58
    cial
    1.57
     puzzles
    1.52
    ¡
    1.47
    mith
    1.46
    iper
    1.45
     blockers
    1.44
    Activations Density 0.012%

    No Known Activations