© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25228
    Prev
    Next
    INDEX
    Explanations

    expressions of "rid" indicating removal or getting rid of something

    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
    320
    +0.11
    0.7%
    111
    +0.11
    0.7%
    180
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.11
    0.01
    180
    +0.11
    0.01
    66
    +0.11
    0.01
    Negative Logits
     least
    -1.85
    ches
    -1.74
     trier
    -1.71
     brightest
    -1.63
    ]>
    -1.58
     best
    -1.57
     smooth
    -1.50
    rapeut
    -1.47
     grown
    -1.44
     better
    -1.44
    POSITIVE LOGITS
    erto
    1.96
    ĻĤ
    1.96
    enstein
    1.89
    ensch
    1.88
    cloth
    1.88
    iculously
    1.81
    arroll
    1.75
    aggio
    1.75
    pora
    1.73
    endar
    1.71
    Activations Density 0.026%

    No Known Activations