© 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. 31208
    Prev
    Next
    INDEX
    Explanations

    words related to responsibilities and opportunities within job descriptions

    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
    195
    +0.10
    0.6%
    140
    +0.10
    0.6%
    30
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.10
    0.01
    66
    +0.10
    0.01
    161
    +0.10
    0.01
    Negative Logits
     saying
    -1.51
     ''
    -1.46
     *"
    -1.44
     tears
    -1.37
     anonymity
    -1.36
     threatened
    -1.36
     mere
    -1.34
    "?"
    -1.34
     discouraged
    -1.33
     thanked
    -1.32
    POSITIVE LOGITS
    IJ
    2.14
    İ
    1.89
    Ĭ
    1.89
    ¶
    1.82
    Į
    1.81
    į
    1.81
    ôt
    1.79
    ĩ
    1.78
    stown
    1.77
    ī
    1.76
    Activations Density 0.035%

    No Known Activations