© 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. 24912
    Prev
    Next
    INDEX
    Explanations

    references to animals and their various species

    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
    23
    +0.16
    0.9%
    42
    +0.13
    0.7%
    52
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.03
    235
    +0.13
    0.04
    180
    +0.11
    0.04
    Negative Logits
    ars
    -1.81
    eners
    -1.72
    room
    -1.62
    cars
    -1.60
    engers
    -1.51
     stops
    -1.50
    es
    -1.47
    usta
    -1.47
    ness
    -1.46
    arp
    -1.45
    POSITIVE LOGITS
     [(\[
    1.58
     fate
    1.46
    wig
    1.42
     prognosis
    1.40
     Freud
    1.38
     |\
    1.37
     deduce
    1.36
     Sachs
    1.32
     hepatitis
    1.32
     faithfully
    1.31
    Activations Density 0.359%

    No Known Activations