© 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 EvalsExportsAPI 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. 26447
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "year" and its derivatives 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
    50
    +0.13
    0.7%
    350
    +0.12
    0.7%
    39
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.13
    0.06
    39
    +0.12
    0.06
    374
    +0.12
    0.05
    Negative Logits
    ĨĴ
    -2.54
    ´
    -2.47
    ĺ
    -2.32
    Ĵ
    -2.31
    ·
    -2.30
    º
    -2.29
    Ĩ
    -2.26
    ·¸
    -2.21
    ½
    -2.17
    Ļª
    -2.12
    POSITIVE LOGITS
    book
    2.23
    nel
    2.16
    lights
    1.95
    ned
    1.86
    forth
    1.84
    ning
    1.78
    nai
    1.75
    nings
    1.75
    walker
    1.74
    ems
    1.70
    Activations Density 0.158%

    No Known Activations