© 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. 1-RES-SM
    11. 25365
    Prev
    Next
    INDEX
    Explanations

    the word "this" used in various contexts

    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
    +0.15
    0.9%
    23
    +0.14
    0.8%
    365
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.15
    0.07
    127
    +0.14
    0.09
    365
    +0.13
    0.06
    Negative Logits
    ļ
    -2.25
    Ļ
    -2.25
    Ļª
    -2.24
    ŀ
    -2.20
    º
    -2.17
    ¼
    -2.09
    ħ
    -2.07
    Ģ
    -2.04
    ´
    -2.04
    ¸
    -2.01
    POSITIVE LOGITS
     yours
    1.99
     yourself
    1.95
     happen
    1.80
     happ
    1.77
     happens
    1.70
     happened
    1.59
    ://
    1.54
     ourselves
    1.53
    ollen
    1.53
    rieve
    1.49
    Activations Density 0.347%

    No Known Activations