© 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. 30189
    Prev
    Next
    INDEX
    Explanations

    phrases indicating simplicity or convenience

    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
    376
    +0.13
    0.7%
    397
    +0.13
    0.7%
    86
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.13
    0.01
    6
    +0.13
    0.01
    325
    +0.11
    0.02
    Negative Logits
     preponderance
    -1.76
    tfn
    -1.51
    pm
    -1.47
    orton
    -1.46
    enth
    -1.46
    elp
    -1.44
     Cause
    -1.43
     Welfare
    -1.43
     whales
    -1.41
    MSO
    -1.41
    POSITIVE LOGITS
    amente
    1.67
     facing
    1.56
    oso
    1.55
    ups
    1.53
    ful
    1.52
     surrounds
    1.48
    ÅĽÄĩ
    1.47
    picker
    1.46
    faced
    1.44
    idable
    1.42
    Activations Density 4.820%

    No Known Activations