© 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. 2-MLP-SM
    11. 24111
    Prev
    Next
    INDEX
    Explanations

    references to medical examinations and procedures related to vision and eye health

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.32
    1.9%
    169
    +0.14
    0.8%
    243
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.32
    0.15
    317
    +0.14
    0.12
    412
    +0.13
    0.12
    Negative Logits
    ·¸
    -3.43
    ³
    -3.20
    ©
    -3.07
    ĵ
    -3.02
    Ļ
    -2.98
    ¤
    -2.93
    ±
    -2.93
    ĥ½
    -2.91
    ·
    -2.90
    °
    -2.77
    POSITIVE LOGITS
    .“
    1.67
     through
    1.62
    ,[@
    1.60
    .[@
    1.60
     (£
    1.47
    als
    1.44
    ,[
    1.43
     via
    1.43
    ]],
    1.39
     spans
    1.38
    Activations Density 3.772%

    No Known Activations