© 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. 2-RES-SM
    11. 26688
    Prev
    Next
    INDEX
    Explanations

    references to clinical trials and outcomes in medical research

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    11
    +0.13
    0.7%
    443
    +0.12
    0.7%
    39
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.13
    0.01
    11
    +0.12
    0.01
    415
    +0.11
    0.01
    Negative Logits
    nis
    -1.70
    ¿
    -1.56
    ches
    -1.53
    ĥ½
    -1.49
    thia
    -1.47
    flies
    -1.44
     severed
    -1.41
    ¡
    -1.39
    chus
    -1.36
    burgh
    -1.35
    POSITIVE LOGITS
    ISPR
    2.23
     msgid
    1.55
    ival
    1.54
    roads
    1.44
    ORY
    1.43
     acknowled
    1.42
    iberal
    1.38
    esar
    1.38
    ---|---
    1.36
    iator
    1.36
    Activations Density 0.040%

    No Known Activations