© 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. Residuals
    9. 1-RES-SM
    11. 29271
    Prev
    Next
    INDEX
    Explanations

    information about clinical research and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    298
    +0.14
    0.8%
    418
    +0.14
    0.8%
    385
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.14
    0.11
    418
    +0.14
    0.01
    385
    +0.12
    0.07
    Negative Logits
    Errno
    -1.72
    ]]
    -1.48
     tolerated
    -1.47
     paradise
    -1.45
    queous
    -1.44
    ux
    -1.43
     downside
    -1.41
     OK
    -1.40
    asone
    -1.39
    ]>
    -1.39
    POSITIVE LOGITS
    Ļª
    2.04
    º
    2.04
    ¾
    1.99
    ±
    1.95
    Ĭ
    1.91
    ¸
    1.89
    ¼
    1.88
    į
    1.86
    Īĺ
    1.79
    ĵ
    1.76
    Activations Density 2.800%

    No Known Activations