© 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. 28759
    Prev
    Next
    INDEX
    Explanations

    instances of the term "cr," likely indicating a focus on contextual references related to "crushing" or "creation."

    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
    410
    +0.13
    0.7%
    502
    +0.13
    0.7%
    470
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.13
    0.02
    468
    +0.13
    0.02
    451
    +0.12
    0.02
    Negative Logits
    erville
    -1.84
    rapeut
    -1.68
    İ
    -1.68
    keit
    -1.67
    lla
    -1.64
    ery
    -1.55
    ments
    -1.49
    ew
    -1.43
    rica
    -1.41
     pleasure
    -1.39
    POSITIVE LOGITS
    amped
    2.05
    annon
    1.65
     compared
    1.63
    iff
    1.60
     embargo
    1.59
     apart
    1.57
    amping
    1.54
    oupe
    1.52
    rant
    1.51
    ató
    1.50
    Activations Density 0.252%

    No Known Activations