© 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. 25763
    Prev
    Next
    INDEX
    Explanations

    instances of the word "problematic" and related expressions of uncertainty or concern

    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
    156
    +0.35
    2.1%
    376
    +0.15
    0.9%
    412
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.35
    0.01
    339
    +0.15
    0.01
    180
    +0.11
    0.01
    Negative Logits
    docs
    -1.67
    itzer
    -1.61
    ikh
    -1.55
    roller
    -1.53
    ene
    -1.41
     evalu
    -1.40
    watson
    -1.37
    ONS
    -1.33
    urer
    -1.32
     breat
    -1.27
    POSITIVE LOGITS
    ĻĤ
    3.20
    ľĵ
    3.13
    ¶
    3.11
    Ł
    3.10
    ·
    3.08
    ¥
    3.00
    ł
    2.93
    ¦
    2.91
    £
    2.89
    ļ
    2.87
    Activations Density 0.029%

    No Known Activations