© 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. 23309
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it"

    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
    81
    +0.15
    0.8%
    429
    +0.14
    0.7%
    38
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.15
    0.03
    81
    +0.14
    0.02
    239
    +0.12
    0.03
    Negative Logits
    ª
    -3.48
    «
    -3.15
    ¿½
    -3.11
    ↵
    -3.04
    -3.04
     ↵
    -3.04
    ↵↵
    -3.04
    ↵
    -3.04
    ↵↵
    -3.04
    ↵
    -3.04
    POSITIVE LOGITS
     favour
    1.67
    idge
    1.57
    lish
    1.55
     encode
    1.40
    ival
    1.40
    itals
    1.39
     poets
    1.38
     among
    1.37
    era
    1.37
    arian
    1.37
    Activations Density 0.396%

    No Known Activations