© 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. 2-MLP-SM
    11. 22832
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or geography

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    499
    +0.16
    0.9%
    455
    +0.12
    0.7%
    417
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.16
    0.07
    302
    +0.12
    0.14
    459
    +0.11
    0.11
    Negative Logits
    onas
    -1.47
     holders
    -1.47
     patrons
    -1.42
     around
    -1.39
    yards
    -1.38
    atures
    -1.37
    oration
    -1.37
     favors
    -1.37
     visitors
    -1.37
    orph
    -1.37
    POSITIVE LOGITS
    ij
    2.03
    Ĵ
    1.78
    ·
    1.72
    ¶
    1.72
    Ŀ
    1.69
    ŀ
    1.59
    º
    1.59
    ļ
    1.55
    ¸
    1.53
    Ģ
    1.53
    Activations Density 3.327%

    No Known Activations