© 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. 24828
    Prev
    Next
    INDEX
    Explanations

    repeated vowels and consonants

    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
    156
    +0.19
    1.1%
    111
    +0.18
    1.0%
    34
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.19
    0.04
    70
    +0.18
    0.02
    497
    +0.13
    -0.01
    Negative Logits
    TRODUCTION
    -1.63
    ging
    -1.58
    iness
    -1.55
    sembling
    -1.55
    ling
    -1.54
     conjecture
    -1.53
     ourselves
    -1.53
    standing
    -1.47
     myself
    -1.47
    dling
    -1.47
    POSITIVE LOGITS
    vier
    1.66
     Office
    1.47
     recipient
    1.45
    ")]
    1.34
     Share
    1.34
    icile
    1.33
     RSS
    1.33
    reads
    1.31
     dÃŃa
    1.29
     prisoner
    1.29
    Activations Density 0.180%

    No Known Activations