© 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. 30125
    Prev
    Next
    INDEX
    Explanations

    dates or references to specific days and 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
    43
    +0.12
    0.6%
    387
    +0.11
    0.6%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.12
    0.02
    493
    +0.11
    0.02
    444
    +0.11
    0.01
    Negative Logits
    ¢
    -2.11
     quo
    -1.93
    versus
    -1.91
    ·¸
    -1.91
    ¶
    -1.88
    ´
    -1.87
    elf
    -1.78
    ¯
    -1.71
    Ĥ¬
    -1.65
    £
    -1.63
    POSITIVE LOGITS
    hew
    1.74
    bell
    1.69
    oral
    1.68
    berry
    1.67
    bourne
    1.64
    terday
    1.62
    ors
    1.59
    quette
    1.59
    ford
    1.58
    weather
    1.54
    Activations Density 0.052%

    No Known Activations