© 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. 2-MLP-SM
    11. 24064
    Prev
    Next
    INDEX
    Explanations

    mentions of "medium" in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.12
    0.7%
    23
    +0.12
    0.7%
    227
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.12
    0.03
    23
    +0.12
    0.01
    55
    +0.11
    0.01
    Negative Logits
    ked
    -1.74
    aeda
    -1.68
    nier
    -1.56
     discloses
    -1.56
    ary
    -1.54
     percent
    -1.50
     millilit
    -1.42
    ados
    -1.39
    coe
    -1.39
     relates
    -1.38
    POSITIVE LOGITS
     `
    1.54
     infamous
    1.50
     Duchess
    1.49
     '#
    1.48
     easiest
    1.47
     ``
    1.46
     poorest
    1.43
     '.
    1.43
    iculously
    1.42
     unfortunate
    1.39
    Activations Density 0.328%

    No Known Activations