© 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. 12625
    Prev
    Next
    INDEX
    Explanations

    elements related to atmosphere and experience

    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
    +0.19
    1.1%
    198
    +0.15
    0.9%
    287
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.19
    0.20
    198
    +0.15
    0.14
    100
    +0.14
    0.15
    Negative Logits
    ĻĤ
    -4.78
    »¿
    -4.50
    ħ
    -4.28
    ¿
    -4.17
    ľĵ
    -4.16
    Ģ
    -4.13
    IJ
    -4.00
    ı
    -3.99
    ĸ´
    -3.96
    ¿½
    -3.94
    POSITIVE LOGITS
    ality
    2.01
    icism
    1.76
    arity
    1.74
    osity
    1.74
    ativity
    1.70
    isma
    1.68
    asm
    1.63
    iness
    1.60
    ism
    1.59
    lication
    1.58
    Activations Density 3.428%

    No Known Activations