© 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. 26667
    Prev
    Next
    INDEX
    Explanations

    instances of the word "attempt."

    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
    +0.17
    0.9%
    257
    +0.12
    0.7%
    404
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.17
    0.03
    83
    +0.12
    0.03
    303
    +0.12
    0.03
    Negative Logits
    MOESM
    -1.77
    watson
    -1.61
    supplementary
    -1.56
    ploid
    -1.55
    jours
    -1.53
    ène
    -1.53
    inx
    -1.52
    ove
    -1.52
    unnumbered
    -1.50
    CSF
    -1.42
    POSITIVE LOGITS
    Īĺ
    2.44
    µ
    1.96
    °
    1.95
    ª
    1.93
    Ĺ
    1.81
    ¢
    1.65
    ħ
    1.65
    ģ
    1.65
    ¹
    1.63
    ĸ
    1.59
    Activations Density 0.575%

    No Known Activations