© 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 EvalsExportsAPI 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. 24448
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reported" and its variations, indicating the presentation of findings or claims

    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
    190
    +0.13
    0.7%
    343
    +0.12
    0.7%
    121
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.13
    0.02
    335
    +0.12
    0.02
    190
    +0.11
    0.02
    Negative Logits
    °
    -3.36
    µ
    -3.24
    ·
    -3.24
    Ķ
    -3.03
    Īĺ
    -2.90
    ³
    -2.87
    ŀ
    -2.87
    ¹
    -2.82
    Ħ
    -2.80
    Ł
    -2.77
    POSITIVE LOGITS
    usiness
    1.76
    iances
    1.75
    zione
    1.72
    useum
    1.71
    legate
    1.60
    arynx
    1.60
    yrinth
    1.57
    auses
    1.54
    oit
    1.51
    antage
    1.46
    Activations Density 0.112%

    No Known Activations