© 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. 26651
    Prev
    Next
    INDEX
    Explanations

    terms related to cancellation and modifications of agreements or transactions

    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
    217
    +0.14
    0.8%
    369
    +0.13
    0.7%
    394
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.11
    255
    +0.13
    0.10
    217
    +0.11
    0.12
    Negative Logits
    ittal
    -1.80
    ĻĤ
    -1.75
    £
    -1.69
    ł
    -1.62
    ounces
    -1.62
    °
    -1.61
    ¶
    -1.47
    izes
    -1.47
    ·
    -1.44
    ¥
    -1.43
    POSITIVE LOGITS
    ées
    1.59
    sworth
    1.59
    rophot
    1.53
    mind
    1.47
     Artists
    1.46
    documentclass
    1.42
     science
    1.41
    ée
    1.39
    ene
    1.36
     styles
    1.36
    Activations Density 1.869%

    No Known Activations