© 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. 28903
    Prev
    Next
    INDEX
    Explanations

    terms related to distinct data entries or groups in a dataset

    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
    380
    +0.15
    0.8%
    30
    +0.14
    0.8%
    164
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.15
    0.02
    380
    +0.14
    0.01
    61
    +0.13
    0.01
    Negative Logits
    Īĺ
    -2.91
    ĸ´
    -2.81
    Ĥ¬
    -2.51
    ´
    -2.42
    ľĵ
    -2.31
    ¿
    -2.27
    ¼
    -2.23
    ľ
    -2.23
    ·¸
    -2.19
    »¿
    -2.17
    POSITIVE LOGITS
    ive
    1.99
    emente
    1.86
    ivism
    1.66
    ures
    1.63
    ives
    1.57
     repertoire
    1.57
    ly
    1.56
    alore
    1.55
    heta
    1.54
    uar
    1.54
    Activations Density 4.733%

    No Known Activations