© 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 EvalsExportsAPI 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. 28409
    Prev
    Next
    INDEX
    Explanations

    references to physicists and the field of 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
    71
    +0.15
    0.8%
    386
    +0.14
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.01
    111
    +0.14
    0.01
    287
    +0.14
    0.01
    Negative Logits
     same
    -1.80
     happier
    -1.55
    ESULT
    -1.51
     hesitation
    -1.50
    ...](
    -1.43
    )$-
    -1.41
     ends
    -1.40
    )$.
    -1.39
     eternity
    -1.36
    |$.
    -1.35
    POSITIVE LOGITS
    "}](#
    2.02
    ists
    1.81
    umns
    1.78
    uscript
    1.50
    iens
    1.49
    ochemical
    1.47
    omechanical
    1.46
    sheet
    1.45
    ģ
    1.45
    ¡
    1.39
    Activations Density 0.014%

    No Known Activations