© 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. 4-RES-SM
    11. 10639
    Prev
    Next
    INDEX
    Explanations

    terms related to gene editing and CRISPR-based therapies for neurological conditions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.19
    1.1%
    307
    +0.15
    0.9%
    333
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.19
    0.03
    333
    +0.15
    0.05
    189
    +0.13
    0.05
    Negative Logits
    []{
    -1.79
     temp
    -1.79
     humidity
    -1.72
     outgoing
    -1.62
    fileID
    -1.57
     Cron
    -1.56
     nominal
    -1.53
     liking
    -1.52
     rpm
    -1.52
     Appellant
    -1.50
    POSITIVE LOGITS
     therapies
    2.88
     strategies
    2.83
     therapeutics
    2.78
     approaches
    2.76
     studies
    2.74
     techniques
    2.44
     interventions
    2.43
     technologies
    2.40
     targeting
    2.35
     methodologies
    2.28
    Activations Density 0.475%

    No Known Activations