© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 26310
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Update," indicating references to changes or notifications

    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
    392
    +0.15
    0.8%
    376
    +0.14
    0.8%
    126
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.15
    0.02
    126
    +0.14
    0.02
    328
    +0.12
    0.02
    Negative Logits
    ĥ½
    -3.58
    ·¸
    -3.17
    ĭ
    -3.15
    Ī
    -3.09
    ĸ´
    -3.09
    Ĵ
    -3.08
    ↵↵
    -3.00
    <|outofrange|>
    -3.00
    č↵
    -3.00
    -3.00
    POSITIVE LOGITS
    ding
    1.84
    dates
    1.82
    zilla
    1.73
    cule
    1.73
    stab
    1.56
    ior
    1.52
    gments
    1.50
    fix
    1.48
    gment
    1.46
    able
    1.43
    Activations Density 0.052%

    No Known Activations