© 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. 22818
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular markers in scientific or medical 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
    +0.26
    1.5%
    23
    +0.14
    0.8%
    427
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.26
    0.02
    390
    +0.14
    0.01
    360
    +0.13
    0.01
    Negative Logits
    <|padding|>
    -3.75
    ↵
    -3.75
    ↵  âĢĥ
    -3.75
    ↵
    -3.75
    -3.75
    č↵
    -3.75
    ↵  ³³³
    -3.75
    ↵
    -3.75
    <|outofrange|>
    -3.75
    -3.75
    POSITIVE LOGITS
     blame
    1.63
     money
    1.51
     psy
    1.49
     negligence
    1.45
     shit
    1.36
     brains
    1.35
     APPEALS
    1.35
     vagu
    1.35
     reputation
    1.32
     judgment
    1.31
    Activations Density 0.338%

    No Known Activations