© 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. 25461
    Prev
    Next
    INDEX
    Explanations

    elements related to HTTP request handling and buffering in programming contexts

    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
    +0.11
    0.6%
    504
    +0.10
    0.6%
    442
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.11
    0.05
    442
    +0.10
    0.04
    420
    +0.10
    0.05
    Negative Logits
    rvert
    -1.64
    opf
    -1.52
    ancell
    -1.49
     yourself
    -1.43
     belong
    -1.37
     artifacts
    -1.34
     herself
    -1.31
    openh
    -1.31
    eren
    -1.31
    ruvate
    -1.30
    POSITIVE LOGITS
    ĨĴ
    1.96
    ĻĤ
    1.95
    ·¸
    1.91
    ¤
    1.76
    ·
    1.60
    Ń
    1.58
     possession
    1.57
    1.57
    <|outofrange|>
    1.57
    1.57
    Activations Density 0.253%

    No Known Activations