© 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. 2-MLP-SM
    11. 27032
    Prev
    Next
    INDEX
    Explanations

    references to default settings or configurations

    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
    173
    +0.13
    0.7%
    46
    +0.11
    0.6%
    112
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.13
    0.02
    46
    +0.11
    0.02
    112
    +0.10
    0.02
    Negative Logits
    ics
    -1.53
    iph
    -1.48
    documentclass
    -1.41
     consumed
    -1.33
    "."
    -1.30
     inhaled
    -1.29
    amycin
    -1.28
     Disease
    -1.28
     consoles
    -1.26
     footballers
    -1.26
    POSITIVE LOGITS
    ĸ´
    2.56
    ĸ
    2.18
    ¿
    2.16
    ı
    2.13
    ķ
    2.08
    »¿
    2.07
    ĨĴ
    2.06
    Ļ
    1.96
    Ĥ¬
    1.90
    ¡
    1.86
    Activations Density 0.198%

    No Known Activations