© 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. 0-MLP-SM
    11. 29132
    Prev
    Next
    INDEX
    Explanations

    references to embryonic stem cells

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.23
    1.3%
    71
    +0.15
    0.9%
    26
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.23
    0.01
    71
    +0.15
    0.01
    259
    +0.13
    0.01
    Negative Logits
     latter
    -1.81
    llo
    -1.61
    off
    -1.47
    ikawa
    -1.46
    ctic
    -1.42
    *).
    -1.41
    owitz
    -1.41
    zzo
    -1.39
    vé
    -1.38
     Appellant
    -1.36
    POSITIVE LOGITS
    stem
    1.57
     applause
    1.47
    amine
    1.42
     aperture
    1.40
    argin
    1.38
    ¿½
    1.37
    "}](#
    1.34
    isations
    1.31
    iss
    1.31
    issance
    1.31
    Activations Density 0.005%

    No Known Activations