© 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. 24951
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    67
    +0.13
    0.8%
    49
    +0.13
    0.7%
    455
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.13
    0.03
    224
    +0.13
    0.03
    55
    +0.13
    0.03
    Negative Logits
     herself
    -2.12
     writes
    -1.61
     himself
    -1.54
    enstein
    -1.51
    ile
    -1.48
    ges
    -1.46
    issance
    -1.44
    ]>
    -1.42
    ility
    -1.42
    ilities
    -1.41
    POSITIVE LOGITS
    ¯
    1.81
    cert
    1.70
    ĻĤ
    1.66
    »¿
    1.63
    «
    1.58
    labelled
    1.58
    Ģ
    1.55
    Ļ
    1.54
    ¡
    1.52
    adium
    1.48
    Activations Density 0.017%

    No Known Activations