© 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. 26038
    Prev
    Next
    INDEX
    Explanations

    references to risks and dangers related to health or safety

    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
    +0.27
    1.5%
    249
    +0.15
    0.9%
    356
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.27
    0.04
    168
    +0.15
    0.03
    335
    +0.11
    0.03
    Negative Logits
    _);
    -1.61
    ios
    -1.60
    []{
    -1.57
     meu
    -1.57
    ;}
    -1.46
    uve
    -1.43
    ugu
    -1.43
    orea
    -1.37
    {"
    -1.35
    ivat
    -1.35
    POSITIVE LOGITS
     explanation
    1.79
     endothelium
    1.60
     engine
    1.55
     teeth
    1.49
    icus
    1.46
     explanations
    1.38
    swers
    1.36
     outcome
    1.36
     contributor
    1.30
    liness
    1.30
    Activations Density 0.183%

    No Known Activations