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

    Neuronpedia

    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. 2-RES-SM
    11. 30119
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences involving emotional struggles and traumatic events

    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
    56
    +0.26
    1.5%
    397
    +0.14
    0.8%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.26
    0.03
    397
    +0.14
    0.11
    155
    +0.12
    0.13
    Negative Logits
    ĥ½
    -2.40
    ·¸
    -2.35
    ĵ
    -2.22
    ĸ´
    -2.11
    ĥ
    -2.06
    ¾
    -2.04
     favor
    -2.00
    ©
    -1.96
    Īĺ
    -1.95
    Ĥ¬
    -1.93
    POSITIVE LOGITS
     collector
    1.97
     battery
    1.80
     casing
    1.78
    stairs
    1.73
     electrolyte
    1.63
     tube
    1.62
     tubes
    1.55
     thrown
    1.54
     batteries
    1.54
     capacitor
    1.52
    Activations Density 3.312%

    No Known Activations