© 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. 0-MLP-SM
    11. 25983
    Prev
    Next
    INDEX
    Explanations

    references to embryos and their preservation processes

    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
    +0.35
    2.2%
    93
    +0.15
    0.9%
    71
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.35
    0.01
    156
    +0.15
    0.01
    17
    +0.14
    0.01
    Negative Logits
    ĥ½
    -3.88
    ¯
    -3.64
    ³
    -3.35
    ·
    -3.31
    £
    -3.30
    ı
    -3.23
    ij
    -3.22
    ķ
    -3.21
    Ĵ
    -3.19
    Ĥ
    -3.17
    POSITIVE LOGITS
    stem
    1.43
    ocs
    1.43
    ong
    1.41
    hower
    1.39
    ime
    1.39
    uit
    1.37
    om
    1.36
    break
    1.35
    ospace
    1.32
    PUT
    1.32
    Activations Density 0.016%

    No Known Activations