© 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. 26609
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gained," indicating a focus on progress, improvement, or acquisition

    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
    376
    +0.21
    1.2%
    148
    +0.12
    0.7%
    317
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.21
    0.02
    254
    +0.12
    0.02
    317
    +0.11
    0.01
    Negative Logits
    ksen
    -1.82
    attle
    -1.66
    onson
    -1.51
    Argued
    -1.51
    isen
    -1.51
    rock
    -1.50
     dass
    -1.50
    akin
    -1.50
    ahan
    -1.49
    cco
    -1.48
    POSITIVE LOGITS
    ĻĤ
    2.66
    ¶
    2.64
    ģ
    2.64
    ¤
    2.52
    ļ
    2.49
    Ĩ
    2.48
    Ģ
    2.46
    ¢
    2.45
    ł
    2.45
    £
    2.37
    Activations Density 0.547%

    No Known Activations