© 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. 2-MLP-SM
    6. 26733
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming-related syntax

    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
    230
    +0.13
    0.7%
    439
    +0.13
    0.7%
    222
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.13
    0.03
    230
    +0.13
    -0.02
    470
    +0.12
    0.12
    Negative Logits
    ³
    -2.98
    ī
    -2.59
    ¥
    -2.56
    ·¸
    -2.50
    ĨĴ
    -2.44
    ¯
    -2.39
    §
    -2.38
                                                   
    -2.37
    <|outofrange|>
    -2.37
    č↵                   
    -2.37
    POSITIVE LOGITS
    youtube
    1.44
     tv
    1.41
    rangle
    1.41
    tub
    1.37
    PCR
    1.36
     hind
    1.33
    sec
    1.33
    tf
    1.32
    bin
    1.32
    olan
    1.31
    Activations Density 2.217%

    No Known Activations