© 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. 0-MLP-SM
    11. 28129
    Prev
    Next
    INDEX
    Explanations

    specific product or item names, particularly related to technology and specifications

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    92
    +0.14
    0.7%
    295
    +0.12
    0.7%
    277
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.14
    0.01
    92
    +0.12
    0.01
    277
    +0.11
    0.01
    Negative Logits
     relation
    -1.65
    acity
    -1.61
    ler
    -1.45
    clamation
    -1.44
     distinction
    -1.36
    iquity
    -1.35
    irection
    -1.35
     my
    -1.32
    ting
    -1.32
     metap
    -1.31
    POSITIVE LOGITS
    Ī
    2.00
    ¤
    1.90
    ı
    1.87
    ↵↵↵
    1.85
    <|outofrange|>
    1.85
    1.85
        ↵
    1.85
    1.85
         ↵
    1.85
    1.85
    Activations Density 0.016%

    No Known Activations