© 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. 25705
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "future."

    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
    107
    +0.12
    0.6%
    365
    +0.11
    0.6%
    46
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.03
    181
    +0.11
    0.03
    336
    +0.10
    0.03
    Negative Logits
    ĻĤ
    -3.86
    Ī
    -3.09
    º
    -3.03
    Ĵ
    -3.01
    «
    -2.98
    ĥ½
    -2.94
    ª
    -2.90
    ·¸
    -2.90
    ½
    -2.79
    ij
    -2.74
    POSITIVE LOGITS
    oral
    1.60
     generations
    1.50
    orld
    1.48
    papers
    1.47
     prospects
    1.47
     developments
    1.44
     outlook
    1.40
     tense
    1.40
     viewing
    1.40
     perspectives
    1.39
    Activations Density 0.131%

    No Known Activations