© 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. 26576
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "eradicating."

    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
    478
    +0.12
    0.6%
    248
    +0.11
    0.6%
    98
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.03
    24
    +0.11
    0.02
    232
    +0.10
    0.01
    Negative Logits
    ¤
    -1.83
    ª
    -1.75
    »
    -1.67
    ted
    -1.63
    ¬
    -1.58
    reflect
    -1.57
    connected
    -1.56
    ģ
    -1.55
    mered
    -1.48
     tolerance
    -1.45
    POSITIVE LOGITS
    ness
    2.11
    amento
    1.84
    "}](#
    1.70
    erior
    1.65
     firms
    1.59
    liers
    1.59
    kov
    1.59
    acional
    1.56
    apine
    1.56
    amiento
    1.55
    Activations Density 0.209%

    No Known Activations