© 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. 28411
    Prev
    Next
    INDEX
    Explanations

    concepts related to multidimensionality

    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
    148
    +0.13
    0.7%
    111
    +0.11
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.13
    0.01
    111
    +0.11
    0.01
    85
    +0.10
    0.01
    Negative Logits
    orems
    -1.72
    ses
    -1.66
    cers
    -1.54
    nez
    -1.51
     authors
    -1.51
    cer
    -1.46
     undocumented
    -1.44
     graduates
    -1.43
    sis
    -1.41
     students
    -1.41
    POSITIVE LOGITS
    imensional
    1.98
    "}](#
    1.80
    irectional
    1.69
    imet
    1.56
    enso
    1.55
    ouin
    1.49
    ette
    1.45
    ue
    1.42
    icult
    1.39
    icro
    1.37
    Activations Density 0.101%

    No Known Activations