© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26804
    Prev
    Next
    INDEX
    Explanations

    terms related to 'eding' or 'feeding'

    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
    503
    +0.11
    0.6%
    253
    +0.11
    0.6%
    198
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.11
    0.01
    503
    +0.11
    0.01
    435
    +0.10
    0.01
    Negative Logits
     ')
    -1.52
    athing
    -1.47
     recruited
    -1.45
     '</
    -1.44
    kered
    -1.43
     asked
    -1.43
    '));
    -1.43
     thanked
    -1.42
     invited
    -1.42
     '_
    -1.41
    POSITIVE LOGITS
    apore
    1.95
    holm
    1.78
    grounds
    1.75
    ground
    1.74
    way
    1.71
    edge
    1.66
    ival
    1.65
    thouse
    1.64
    ļ
    1.64
    ±
    1.61
    Activations Density 0.011%

    No Known Activations