© 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. 2-MLP-SM
    11. 27115
    Prev
    Next
    INDEX
    Explanations

    conditions and restrictions related to modification and redistribution of content or software

    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
    3
    +0.12
    0.7%
    201
    +0.12
    0.7%
    76
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.12
    0.10
    201
    +0.12
    -0.01
    257
    +0.11
    0.10
    Negative Logits
    soon
    -1.64
    along
    -1.60
    émon
    -1.56
    "));
    -1.56
    ill
    -1.52
    arma
    -1.44
    )));
    -1.43
    else
    -1.42
     ))
    -1.42
     );
    -1.41
    POSITIVE LOGITS
    ·¸
    2.25
    ¸
    1.99
    ľ
    1.88
    «
    1.86
    ļ
    1.79
    Į
    1.73
    ij
    1.73
    ł
    1.71
    ¿½
    1.70
    ¾
    1.68
    Activations Density 3.351%

    No Known Activations