© 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. 2-MLP-SM
    6. 25943
    Prev
    Next
    INDEX
    Explanations

    references to citations or annotations in academic texts

    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
    +0.17
    1.0%
    423
    +0.13
    0.7%
    337
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.17
    0.03
    459
    +0.13
    0.02
    331
    +0.11
    0.02
    Negative Logits
     someone
    -1.81
    ł
    -1.66
    uscular
    -1.56
    Ļ
    -1.51
    eren
    -1.48
    IJ
    -1.48
    ¦
    -1.47
    ¿
    -1.45
    °
    -1.44
    ±
    -1.43
    POSITIVE LOGITS
     campaign
    1.65
    adesh
    1.53
    azine
    1.50
    ://
    1.47
    ophosph
    1.44
    campaign
    1.42
    ressor
    1.40
     cavity
    1.39
     formula
    1.35
    iaz
    1.34
    Activations Density 0.108%

    No Known Activations