© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25785
    Prev
    Next
    INDEX
    Explanations

    references to storage capacity and specifications of devices

    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
    205
    +0.17
    1.0%
    23
    +0.15
    0.8%
    232
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.12
    23
    +0.15
    0.07
    56
    +0.13
    0.12
    Negative Logits
     Kick
    -1.67
    boarding
    -1.66
    idas
    -1.49
    agne
    -1.42
     Kong
    -1.42
     Leone
    -1.42
     Gaming
    -1.41
     Olymp
    -1.37
    ppler
    -1.34
     League
    -1.30
    POSITIVE LOGITS
     0000000000000000000000000000000000
    1.77
    ITED
    1.57
    inner
    1.57
    ]));
    1.56
    )));
    1.53
     continued
    1.51
    ↵³³
    1.47
    underset
    1.47
    }_{
    1.46
    tid
    1.45
    Activations Density 2.035%

    No Known Activations