© 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. 26010
    Prev
    Next
    INDEX
    Explanations

    mentions of cDNA, a type of DNA synthesized from a messenger RNA template

    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
    30
    +0.12
    0.7%
    26
    +0.11
    0.6%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.12
    0.00
    279
    +0.11
    0.01
    26
    +0.11
    0.00
    Negative Logits
    ¼
    -2.67
    ¯
    -2.60
    ½
    -2.52
    ĸ´
    -2.44
    ĭ
    -2.42
    Ĺ
    -2.38
    ĥ½
    -2.37
    į
    -2.28
    ¸
    -2.22
    ·¸
    -2.21
    POSITIVE LOGITS
    ong
    1.66
     festivals
    1.49
    ONG
    1.44
    fest
    1.41
    falls
    1.41
    pack
    1.39
     thriller
    1.39
     registers
    1.38
    coin
    1.38
    uary
    1.38
    Activations Density 0.004%

    No Known Activations