© 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. 28851
    Prev
    Next
    INDEX
    Explanations

    specific references to medical or theological concepts and qualifications

    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
    263
    +0.16
    0.9%
    185
    +0.13
    0.7%
    278
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.16
    0.36
    23
    +0.13
    0.31
    494
    +0.12
    0.25
    Negative Logits
    Īĺ
    -2.43
    ĻĤ
    -2.39
    ĭ
    -2.28
    ļ
    -2.25
    ĩ
    -2.20
    Ļª
    -2.10
    ª
    -2.10
    ŀ
    -2.07
    ī
    -2.06
    §
    -2.05
    POSITIVE LOGITS
     pride
    1.64
    ounder
    1.54
    irk
    1.52
    raid
    1.47
     sooner
    1.44
     pains
    1.42
     trouble
    1.42
    igate
    1.39
    pler
    1.39
    probe
    1.39
    Activations Density 3.050%

    No Known Activations