© 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. 0-MLP-SM
    11. 27859
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "raised" in various 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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.19
    1.0%
    246
    +0.14
    0.8%
    352
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.19
    0.03
    246
    +0.14
    0.02
    319
    +0.14
    0.01
    Negative Logits
    UTERS
    -1.82
    yrus
    -1.76
    ksen
    -1.70
    illance
    -1.55
    iless
    -1.54
    iest
    -1.43
    ---|---
    -1.41
    aught
    -1.41
    ches
    -1.39
    oit
    -1.38
    POSITIVE LOGITS
    hold
    1.71
     eyebrows
    1.46
     enough
    1.40
     thresholds
    1.39
     age
    1.38
     hold
    1.37
     Minn
    1.37
     currents
    1.35
     tendencies
    1.31
    dimen
    1.31
    Activations Density 0.023%

    No Known Activations