© 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. 23474
    Prev
    Next
    INDEX
    Explanations

    license identifiers and copyright notations in a text

    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
    505
    +0.13
    0.7%
    156
    +0.12
    0.7%
    189
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.13
    0.04
    505
    +0.12
    0.03
    202
    +0.12
    0.03
    Negative Logits
    chart
    -1.66
    âĢŁ
    -1.61
    charts
    -1.49
    ]{})
    -1.49
    00000000000000000000000000000000
    -1.43
     Statement
    -1.43
    ))\
    -1.34
     similarly
    -1.33
    \])]{}
    -1.30
    fficients
    -1.29
    POSITIVE LOGITS
     dynasty
    1.60
     breath
    1.54
     classics
    1.53
    onen
    1.51
     punishment
    1.48
     refrig
    1.46
     ambulance
    1.44
     suburb
    1.43
     favourite
    1.43
     home
    1.42
    Activations Density 0.141%

    No Known Activations