© 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. 25451
    Prev
    Next
    INDEX
    Explanations

    the word "from"

    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
    356
    +0.12
    0.6%
    327
    +0.10
    0.6%
    415
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.12
    0.08
    440
    +0.10
    0.03
    70
    +0.10
    0.05
    Negative Logits
    bol
    -1.75
    CIAL
    -1.72
    gauge
    -1.44
    heim
    -1.44
    ABA
    -1.44
    etr
    -1.38
    ether
    -1.34
     checkpoint
    -1.30
     van
    -1.29
    ticos
    -1.28
    POSITIVE LOGITS
     Wales
    1.82
     celebrate
    1.48
     palate
    1.45
    ogether
    1.45
    continue
    1.44
    >';
    1.37
    »¿
    1.34
    ugu
    1.34
    edly
    1.33
    phon
    1.30
    Activations Density 0.471%

    No Known Activations