© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27759
    Prev
    Next
    INDEX
    Explanations

    terms related to processes of emitting or producing something

    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
    376
    +0.23
    1.3%
    156
    +0.20
    1.2%
    148
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.23
    0.01
    308
    +0.20
    0.01
    463
    +0.15
    0.01
    Negative Logits
    ydr
    -1.66
    ours
    -1.34
    ress
    -1.33
    rained
    -1.30
    going
    -1.29
    resses
    -1.28
    dorff
    -1.28
    iele
    -1.27
     brewing
    -1.27
    dered
    -1.26
    POSITIVE LOGITS
     puff
    1.51
     wing
    1.50
     presum
    1.41
    gun
    1.37
    minute
    1.34
     vest
    1.32
     buzz
    1.32
     vital
    1.29
     obstruction
    1.28
     signal
    1.25
    Activations Density 0.006%

    No Known Activations