© 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 EvalsExportsAPI 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. 26495
    Prev
    Next
    INDEX
    Explanations

    terms related to administrative roles and permissions

    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
    156
    +0.16
    1.0%
    392
    +0.12
    0.7%
    167
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.16
    0.02
    355
    +0.12
    0.02
    307
    +0.11
    0.02
    Negative Logits
     true
    -1.70
    ational
    -1.62
    eworthy
    -1.59
    opic
    -1.58
     normal
    -1.56
     embryonic
    -1.51
    UNC
    -1.48
     between
    -1.44
     shorter
    -1.43
    oxic
    -1.42
    POSITIVE LOGITS
    ister
    2.52
    ¾
    2.42
    »
    2.27
    isters
    2.14
    »¿
    2.10
    ½
    2.10
    ¼
    2.08
    ¡
    2.01
    «
    2.00
    dom
    1.93
    Activations Density 0.124%

    No Known Activations