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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26488
    Prev
    Next
    INDEX
    Explanations

    licensing and copyright information

    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
    +0.13
    0.7%
    218
    +0.12
    0.6%
    134
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.13
    0.02
    376
    +0.12
    0.01
    420
    +0.11
    0.01
    Negative Logits
    '));
    -1.54
    ĨĴ
    -1.50
    ')$
    -1.46
    '))
    -1.44
    ()));
    -1.43
    ľĵ
    -1.43
    ());
    -1.42
     PubMed
    -1.41
     successful
    -1.38
    ');
    -1.37
    POSITIVE LOGITS
    hardt
    1.81
    mann
    1.71
     Than
    1.65
    igue
    1.62
    iencies
    1.58
    than
    1.58
    iani
    1.57
    iors
    1.57
     than
    1.57
    ffer
    1.52
    Activations Density 0.055%

    No Known Activations