© 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. 23135
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'Z' in various contexts

    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
    +0.21
    1.1%
    470
    +0.15
    0.8%
    76
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.21
    0.01
    76
    +0.15
    0.02
    105
    +0.10
    0.02
    Negative Logits
    cept
    -1.62
    ships
    -1.61
    ictionary
    -1.53
    agles
    -1.47
    versed
    -1.45
    lem
    -1.44
     owners
    -1.44
    worthy
    -1.42
    ="@+
    -1.42
    izen
    -1.38
    POSITIVE LOGITS
     suppression
    1.41
    ↵Č
    1.40
     gag
    1.31
     Saddam
    1.29
     Taliban
    1.29
    impl
    1.26
    dal
    1.25
     aug
    1.23
    anking
    1.23
    anyl
    1.23
    Activations Density 0.157%

    No Known Activations