© 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. 29171
    Prev
    Next
    INDEX
    Explanations

    references to chemistry and related scientific concepts

    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
    +0.21
    1.2%
    376
    +0.09
    0.5%
    2
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.21
    0.01
    230
    +0.09
    0.01
    54
    +0.09
    0.01
    Negative Logits
    ¯
    -3.68
    ¿
    -3.36
    ĥ½
    -3.22
    ³
    -3.19
    ±
    -3.15
    Ĭ
    -3.11
    µ
    -3.10
    ½
    -3.05
    ´
    -3.01
    ĭ
    -3.01
    POSITIVE LOGITS
    plit
    1.72
    hemat
    1.62
    eral
    1.61
    fluid
    1.52
    cores
    1.51
    ically
    1.48
    plain
    1.47
    pere
    1.47
    entially
    1.41
    helm
    1.41
    Activations Density 0.405%

    No Known Activations