© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27846
    Prev
    Next
    INDEX
    Explanations

    question marks and phrases indicating confusion or inquiry

    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
    389
    +0.13
    0.8%
    505
    +0.12
    0.7%
    278
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.13
    0.01
    389
    +0.12
    0.01
    135
    +0.11
    0.01
    Negative Logits
     compared
    -1.78
     ([
    -1.71
     Strip
    -1.52
    while
    -1.51
    rightarrow
    -1.48
    ocal
    -1.47
    front
    -1.44
     Frontier
    -1.42
     spots
    -1.38
     ([@
    -1.34
    POSITIVE LOGITS
    ·¸
    5.18
    ĻĤ
    5.18
    Į
    5.12
    ®
    5.04
    ½
    4.98
    ŀ
    4.97
    ↵
    4.93
                ↵
    4.93
    4.93
    ↵↵
    4.93
    Activations Density 0.014%

    No Known Activations