© 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. 24193
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to suffering and distress

    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
    351
    +0.13
    0.7%
    41
    +0.12
    0.7%
    70
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.13
    0.04
    67
    +0.12
    0.03
    335
    +0.12
    0.03
    Negative Logits
    aused
    -1.77
     mess
    -1.57
    rans
    -1.52
     minimized
    -1.50
     happening
    -1.50
    ird
    -1.45
    emphasis
    -1.43
    destroy
    -1.42
    omb
    -1.42
    (:
    -1.41
    POSITIVE LOGITS
    izumab
    1.59
     admissibility
    1.47
    coat
    1.47
     supplements
    1.45
     copies
    1.45
    ipore
    1.44
     bottles
    1.44
    arner
    1.41
    gester
    1.40
     anhydr
    1.39
    Activations Density 0.384%

    No Known Activations